🎯 Top Personalized Recommendations
LAMSADE, Univ ParisDaup
Why we think this paper is great for you:
This paper directly addresses in-memory indexing and querying within data preparation pipelines, which is highly relevant to your interest in efficient data management and data warehousing. It explores methods for understanding and utilizing data provenance, a key aspect of data quality and analysis.
This paper directly addresses in-memory indexing and querying within data preparation pipelines, which is highly relevant to your interest in efficient data management and data warehousing. It explores methods for understanding and utilizing data provenance, a key aspect of data quality and analysis.
Abstract
Data provenance has numerous applications in the context of data preparation pipelines. It can be used for debugging faulty pipelines, interpreting results, verifying fairness, and identifying data quality issues, which may affect the sources feeding the pipeline execution. In this paper, we present an indexing mechanism to efficiently capture and query pipeline provenance. Our solution leverages tensors to capture fine-grained provenance of data processing operations, using minimal memory. In addition to record-level lineage relationships, we provide finer granularity at the attribute level. This is achieved by augmenting tensors, which capture retrospective provenance, with prospective provenance information, drawing connections between input and output schemas of data processing operations. We demonstrate how these two types of provenance (retrospective and prospective) can be combined to answer a broad range of provenance queries efficiently, and show effectiveness through evaluation exercises using both real and synthetic data.
Data provenance has numerous applications in the context of data preparation pipelines. It can be used for debugging faulty pipelines, interpreting results, verifying fairness, and identifying data quality issues, which may affect the sources feeding the pipeline execution. In this paper, we present an indexing mechanism to efficiently capture and query pipeline provenance. Our solution leverages tensors to capture fine-grained provenance of data processing operations, using minimal memory. In addition to record-level lineage relationships, we provide finer granularity at the attribute level. This is achieved by augmenting tensors, which capture retrospective provenance, with prospective provenance information, drawing connections between input and output schemas of data processing operations. We demonstrate how these two types of provenance (retrospective and prospective) can be combined to answer a broad range of provenance queries efficiently, and show effectiveness through evaluation exercises using both real and synthetic data.
AI Summary
- The paper introduces a novel in-memory mechanism leveraging sparse binary tensors to efficiently capture fine-grained provenance (record and attribute-value level) in data preparation pipelines, enabling dynamic exploration during development. [3]
- Attribute-level provenance is achieved by augmenting record-level tensors with minimal metadata (bitsets) that specify input/output column correspondences and data manipulation types, avoiding the high overhead of explicitly tracking every attribute value. [3]
- The system supports a broad range of record-based and attribute-value-based provenance queries (forward, backward, co-contributory, co-dependency, how-provenance) by leveraging tensor slicing, projection, and Einstein summation. [3]
- Provenance of a Data Processing Operation: Encoded using an order n+1 binary tensor T(DP), where T(DP)(o, i1, ..., in) = 1 if output record DO_o is provenance-wise derived from input records (DI1_i1, ..., DIn_in). [3]
- Sparse Binary Tensors: N-dimensional arrays mapping multi-indices to boolean values (0 or 1), used to encode derivation relationships between data records with minimal memory. [3]
- Optimized Tensor Representation: A rooted acyclic graph structure for sparse binary tensors, where nodes represent datasets, record indices, and full provenance triples, designed for efficient lineage traversal. [3]
- A specialized rooted acyclic graph structure is designed for sparse binary tensors, significantly reducing lineage query processing time from O(T) (scanning) to O(d) (tree height, typically 3 accesses) compared to standard sparse tensor formats. [2]
- The solution employs a hybrid provenance capture strategy, using observation-based methods for operations preserving data frame indices and active capture for operations that do not, balancing intrusiveness and computational cost. [2]
- Data processing operations are categorized into 'localized' (recomputable from provenance-related inputs) and 'contextual' (requiring full dataset context), allowing selective materialization of input datasets to balance memory usage and recomputation efficiency. [2]
- Empirical evaluations demonstrate the solution's effectiveness in minimizing storage space for provenance encoding, reducing processing overhead during capture, and accelerating provenance query execution. [2]
University of Toronto
Why we think this paper is great for you:
You will find this paper highly relevant as it delves into applying relational concepts and analytical queries to unstructured data, a critical challenge in modern database design. It offers insights into structuring diverse data types for effective analysis.
You will find this paper highly relevant as it delves into applying relational concepts and analytical queries to unstructured data, a critical challenge in modern database design. It offers insights into structuring diverse data types for effective analysis.
Abstract
Unstructured data is pervasive, but analytical queries demand structured representations, creating a significant extraction challenge. Existing methods like RAG lack schema awareness and struggle with cross-document alignment, leading to high error rates. We propose ReDD (Relational Deep Dive), a framework that dynamically discovers query-specific schemas, populates relational tables, and ensures error-aware extraction with provable guarantees. ReDD features a two-stage pipeline: (1) Iterative Schema Discovery (ISD) identifies minimal, joinable schemas tailored to each query, and (2) Tabular Data Population (TDP) extracts and corrects data using lightweight classifiers trained on LLM hidden states. A main contribution of ReDD is SCAPE, a statistically calibrated method for error detection with coverage guarantees, and SCAPE-HYB, a hybrid approach that optimizes the trade-off between accuracy and human correction costs. Experiments across diverse datasets demonstrate ReDD's effectiveness, reducing data extraction errors from up to 30% to below 1% while maintaining high schema completeness (100% recall) and precision. ReDD's modular design enables fine-grained control over accuracy-cost trade-offs, making it a robust solution for high-stakes analytical queries over unstructured corpora.
Unstructured data is pervasive, but analytical queries demand structured representations, creating a significant extraction challenge. Existing methods like RAG lack schema awareness and struggle with cross-document alignment, leading to high error rates. We propose ReDD (Relational Deep Dive), a framework that dynamically discovers query-specific schemas, populates relational tables, and ensures error-aware extraction with provable guarantees. ReDD features a two-stage pipeline: (1) Iterative Schema Discovery (ISD) identifies minimal, joinable schemas tailored to each query, and (2) Tabular Data Population (TDP) extracts and corrects data using lightweight classifiers trained on LLM hidden states. A main contribution of ReDD is SCAPE, a statistically calibrated method for error detection with coverage guarantees, and SCAPE-HYB, a hybrid approach that optimizes the trade-off between accuracy and human correction costs. Experiments across diverse datasets demonstrate ReDD's effectiveness, reducing data extraction errors from up to 30% to below 1% while maintaining high schema completeness (100% recall) and precision. ReDD's modular design enables fine-grained control over accuracy-cost trade-offs, making it a robust solution for high-stakes analytical queries over unstructured corpora.
Centrum Wiskunde & Inform
Why we think this paper is great for you:
This paper explores natural language interfaces for tabular data analysis and the nuances of queries, directly aligning with your interest in SQL and interacting with relational databases. It provides valuable perspectives on improving query specification and understanding.
This paper explores natural language interfaces for tabular data analysis and the nuances of queries, directly aligning with your interest in SQL and interacting with relational databases. It provides valuable perspectives on improving query specification and understanding.
Abstract
Natural language interfaces to tabular data must handle ambiguities inherent to queries. Instead of treating ambiguity as a deficiency, we reframe it as a feature of cooperative interaction, where the responsibility of query specification is shared among the user and the system. We develop a principled framework distinguishing cooperative queries, i.e., queries that yield a resolvable interpretation, from uncooperative queries that cannot be resolved. Applying the framework to evaluations for tabular question answering and analysis, we analyze the queries in 15 popular datasets, and observe an uncontrolled mixing of query types neither adequate for evaluating a system's execution accuracy nor for evaluating interpretation capabilities. Our framework and analysis of queries shifts the perspective from fixing ambiguity to embracing cooperation in resolving queries. This reflection enables more informed design and evaluation for natural language interfaces for tabular data, for which we outline implications and directions for future research.
Natural language interfaces to tabular data must handle ambiguities inherent to queries. Instead of treating ambiguity as a deficiency, we reframe it as a feature of cooperative interaction, where the responsibility of query specification is shared among the user and the system. We develop a principled framework distinguishing cooperative queries, i.e., queries that yield a resolvable interpretation, from uncooperative queries that cannot be resolved. Applying the framework to evaluations for tabular question answering and analysis, we analyze the queries in 15 popular datasets, and observe an uncontrolled mixing of query types neither adequate for evaluating a system's execution accuracy nor for evaluating interpretation capabilities. Our framework and analysis of queries shifts the perspective from fixing ambiguity to embracing cooperation in resolving queries. This reflection enables more informed design and evaluation for natural language interfaces for tabular data, for which we outline implications and directions for future research.
Why we think this paper is great for you:
This paper focuses on integrating diverse data for analytical purposes, which is central to effective data warehousing and database design practices. It showcases how different data sources can be unified to support complex decision-making.
This paper focuses on integrating diverse data for analytical purposes, which is central to effective data warehousing and database design practices. It showcases how different data sources can be unified to support complex decision-making.
Abstract
Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and operational data under tight time constraints. We present Geothermal Analytics and Intelligent Agent, or GAIA, an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA Digital Twin, or DT, which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA's specialized capability for handling complex geothermal-related tasks, we curate a benchmark test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system's performance. We envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.
Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and operational data under tight time constraints. We present Geothermal Analytics and Intelligent Agent, or GAIA, an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA Digital Twin, or DT, which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA's specialized capability for handling complex geothermal-related tasks, we curate a benchmark test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system's performance. We envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.
University of Illinois at
Why we think this paper is great for you:
Given your interest in various database types, this paper on analytical queries for unstructured data will be insightful. It addresses the significant challenge of extracting meaningful information from data that doesn't conform to traditional structures.
Given your interest in various database types, this paper on analytical queries for unstructured data will be insightful. It addresses the significant challenge of extracting meaningful information from data that doesn't conform to traditional structures.
Abstract
Unstructured data, in the form of text, images, video, and audio, is produced at exponentially higher rates. In tandem, machine learning (ML) methods have become increasingly powerful at analyzing unstructured data. Modern ML methods can now detect objects in images, understand actions in videos, and even classify complex legal texts based on legal intent. Combined, these trends make it increasingly feasible for analysts and researchers to automatically understand the "real world." However, there are major challenges in deploying these techniques: 1) executing queries efficiently given the expense of ML methods, 2) expressing queries over bespoke forms of data, and 3) handling errors in ML methods. In this monograph, we discuss challenges and advances in data management systems for unstructured data using ML, with a particular focus on video analytics. Using ML to answer queries introduces new challenges.First, even turning user intent into queries can be challenging: it is not obvious how to express a query of the form "select instances of cars turning left." Second, ML models can be orders of magnitude more expensive compared to processing traditional structured data. Third, ML models and the methods to accelerate analytics with ML models can be error-prone. Recent work in the data management community has aimed to address all of these challenges. Users can now express queries via user-defined functions, opaquely through standard structured schemas, and even by providing examples. Given a query, recent work focuses on optimizing queries by approximating expensive "gold" methods with varying levels of guarantees. Finally, to handle errors in ML models, recent work has focused on applying outlier and drift detection to data analytics with ML.
Unstructured data, in the form of text, images, video, and audio, is produced at exponentially higher rates. In tandem, machine learning (ML) methods have become increasingly powerful at analyzing unstructured data. Modern ML methods can now detect objects in images, understand actions in videos, and even classify complex legal texts based on legal intent. Combined, these trends make it increasingly feasible for analysts and researchers to automatically understand the "real world." However, there are major challenges in deploying these techniques: 1) executing queries efficiently given the expense of ML methods, 2) expressing queries over bespoke forms of data, and 3) handling errors in ML methods. In this monograph, we discuss challenges and advances in data management systems for unstructured data using ML, with a particular focus on video analytics. Using ML to answer queries introduces new challenges.First, even turning user intent into queries can be challenging: it is not obvious how to express a query of the form "select instances of cars turning left." Second, ML models can be orders of magnitude more expensive compared to processing traditional structured data. Third, ML models and the methods to accelerate analytics with ML models can be error-prone. Recent work in the data management community has aimed to address all of these challenges. Users can now express queries via user-defined functions, opaquely through standard structured schemas, and even by providing examples. Given a query, recent work focuses on optimizing queries by approximating expensive "gold" methods with varying levels of guarantees. Finally, to handle errors in ML models, recent work has focused on applying outlier and drift detection to data analytics with ML.
University of Washington
Why we think this paper is great for you:
This paper discusses managing diverse schemas in complex environments, a topic that touches upon the challenges of database design and integration. It offers a perspective on how different data structures interact within a system.
This paper discusses managing diverse schemas in complex environments, a topic that touches upon the challenges of database design and integration. It offers a perspective on how different data structures interact within a system.
Abstract
LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on $\tau^2$-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation.
LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on $\tau^2$-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation.
Edison Scientific Inc, 1
Why we think this paper is great for you:
This paper explores autonomous scientific discovery driven by data, highlighting the importance of robust data analysis and management in research. It provides a broader context for how data-centric approaches are applied to complex problems.
This paper explores autonomous scientific discovery driven by data, highlighting the importance of robust data analysis and management in research. It provides a broader context for how data-centric approaches are applied to complex problems.
Abstract
Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.
Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.
AI Agents
Shanghai Jiaotong Univer
Abstract
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.
AI and Society
KFUPM King Fahd Univeris
Abstract
Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI values. This study investigates how closely LLMs' value preferences align with those of two human groups: a US-representative sample and AI practitioners. We evaluate 23 LLMs across four tasks: (T1) selecting key responsible AI values, (T2) rating their importance in specific contexts, (T3) resolving trade-offs between competing values, and (T4) prioritizing software requirements that embody those values. The results show that LLMs generally align more closely with AI practitioners than with the US-representative sample, emphasizing fairness, privacy, transparency, safety, and accountability. However, inconsistencies appear between the values that LLMs claim to uphold (Tasks 1-3) and the way they prioritize requirements (Task 4), revealing gaps in faithfulness between stated and applied behavior. These findings highlight the practical risk of relying on LLMs in requirements engineering without human oversight and motivate the need for systematic approaches to benchmark, interpret, and monitor value alignment in AI-assisted software development.
Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI values. This study investigates how closely LLMs' value preferences align with those of two human groups: a US-representative sample and AI practitioners. We evaluate 23 LLMs across four tasks: (T1) selecting key responsible AI values, (T2) rating their importance in specific contexts, (T3) resolving trade-offs between competing values, and (T4) prioritizing software requirements that embody those values. The results show that LLMs generally align more closely with AI practitioners than with the US-representative sample, emphasizing fairness, privacy, transparency, safety, and accountability. However, inconsistencies appear between the values that LLMs claim to uphold (Tasks 1-3) and the way they prioritize requirements (Task 4), revealing gaps in faithfulness between stated and applied behavior. These findings highlight the practical risk of relying on LLMs in requirements engineering without human oversight and motivate the need for systematic approaches to benchmark, interpret, and monitor value alignment in AI-assisted software development.
The University of Tokyo
Abstract
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr. AI Scientist, a state-of-the-art autonomous AI scientist system that mimics the core research workflow of a novice student researcher: Given the baseline paper from the human mentor, it analyzes its limitations, formulates novel hypotheses for improvement, validates them through rigorous experimentation, and writes a paper with the results. Unlike previous approaches that assume full automation or operate on small-scale code, Jr. AI Scientist follows a well-defined research workflow and leverages modern coding agents to handle complex, multi-file implementations, leading to scientifically valuable contributions. For evaluation, we conducted automated assessments using AI Reviewers, author-led evaluations, and submissions to Agents4Science, a venue dedicated to AI-driven scientific contributions. The findings demonstrate that Jr. AI Scientist generates papers receiving higher review scores than existing fully automated systems. Nevertheless, we identify important limitations from both the author evaluation and the Agents4Science reviews, indicating the potential risks of directly applying current AI Scientist systems and key challenges for future research. Finally, we comprehensively report various risks identified during development. We hope these insights will deepen understanding of current progress and risks in AI Scientist development.
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr. AI Scientist, a state-of-the-art autonomous AI scientist system that mimics the core research workflow of a novice student researcher: Given the baseline paper from the human mentor, it analyzes its limitations, formulates novel hypotheses for improvement, validates them through rigorous experimentation, and writes a paper with the results. Unlike previous approaches that assume full automation or operate on small-scale code, Jr. AI Scientist follows a well-defined research workflow and leverages modern coding agents to handle complex, multi-file implementations, leading to scientifically valuable contributions. For evaluation, we conducted automated assessments using AI Reviewers, author-led evaluations, and submissions to Agents4Science, a venue dedicated to AI-driven scientific contributions. The findings demonstrate that Jr. AI Scientist generates papers receiving higher review scores than existing fully automated systems. Nevertheless, we identify important limitations from both the author evaluation and the Agents4Science reviews, indicating the potential risks of directly applying current AI Scientist systems and key challenges for future research. Finally, we comprehensively report various risks identified during development. We hope these insights will deepen understanding of current progress and risks in AI Scientist development.
Deep Learning
City St Georges, Univer
Abstract
Artificial Intelligence (AI) is a powerful new language of science as evidenced by recent Nobel Prizes in chemistry and physics that recognized contributions to AI applied to those areas. Yet, this new language lacks semantics, which makes AI's scientific discoveries unsatisfactory at best. With the purpose of uncovering new facts but also improving our understanding of the world, AI-based science requires formalization through a framework capable of translating insight into comprehensible scientific knowledge. In this paper, we argue that logic offers an adequate framework. In particular, we use logic in a neurosymbolic framework to offer a much needed semantics for deep learning, the neural network-based technology of current AI. Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied. Instead, there is a plethora of encoding and knowledge extraction approaches designed for particular cases. To rectify this, we introduced a framework for semantic encoding, making explicit the mapping between neural networks and logic, and characterizing the common ingredients of the various existing approaches. In this paper, we describe succinctly and exemplify how logical semantics and neural networks are linked through this framework, we review some of the most prominent approaches and techniques developed for neural encoding and knowledge extraction, provide a formal definition of our framework, and discuss some of the difficulties of identifying a semantic encoding in practice in light of analogous problems in the philosophy of mind.
Artificial Intelligence (AI) is a powerful new language of science as evidenced by recent Nobel Prizes in chemistry and physics that recognized contributions to AI applied to those areas. Yet, this new language lacks semantics, which makes AI's scientific discoveries unsatisfactory at best. With the purpose of uncovering new facts but also improving our understanding of the world, AI-based science requires formalization through a framework capable of translating insight into comprehensible scientific knowledge. In this paper, we argue that logic offers an adequate framework. In particular, we use logic in a neurosymbolic framework to offer a much needed semantics for deep learning, the neural network-based technology of current AI. Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied. Instead, there is a plethora of encoding and knowledge extraction approaches designed for particular cases. To rectify this, we introduced a framework for semantic encoding, making explicit the mapping between neural networks and logic, and characterizing the common ingredients of the various existing approaches. In this paper, we describe succinctly and exemplify how logical semantics and neural networks are linked through this framework, we review some of the most prominent approaches and techniques developed for neural encoding and knowledge extraction, provide a formal definition of our framework, and discuss some of the difficulties of identifying a semantic encoding in practice in light of analogous problems in the philosophy of mind.
VISTAMILK, Dublin City Un
Abstract
Grasslands, constituting the world's second-largest terrestrial carbon sink, play a crucial role in biodiversity and the regulation of the carbon cycle. Currently, the Irish dairy sector, a significant economic contributor, grapples with challenges related to profitability and sustainability. Presently, grass growth forecasting relies on impractical mechanistic models. In response, we propose deep learning models tailored for univariate datasets, presenting cost-effective alternatives. Notably, a temporal convolutional network designed for forecasting Perennial Ryegrass growth in Cork exhibits high performance, leveraging historical grass height data with RMSE of 2.74 and MAE of 3.46. Validation across a comprehensive dataset spanning 1,757 weeks over 34 years provides insights into optimal model configurations. This study enhances our understanding of model behavior, thereby improving reliability in grass growth forecasting and contributing to the advancement of sustainable dairy farming practices.
Grasslands, constituting the world's second-largest terrestrial carbon sink, play a crucial role in biodiversity and the regulation of the carbon cycle. Currently, the Irish dairy sector, a significant economic contributor, grapples with challenges related to profitability and sustainability. Presently, grass growth forecasting relies on impractical mechanistic models. In response, we propose deep learning models tailored for univariate datasets, presenting cost-effective alternatives. Notably, a temporal convolutional network designed for forecasting Perennial Ryegrass growth in Cork exhibits high performance, leveraging historical grass height data with RMSE of 2.74 and MAE of 3.46. Validation across a comprehensive dataset spanning 1,757 weeks over 34 years provides insights into optimal model configurations. This study enhances our understanding of model behavior, thereby improving reliability in grass growth forecasting and contributing to the advancement of sustainable dairy farming practices.
We did not find tons of content matching your interests we've included some additional topics that are popular. Also be aware that if the topics is not present in arxiv we wont be able to recommend it.
AI Agents
University of Washington
Abstract
LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on $\tau^2$-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation.
LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on $\tau^2$-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation.
Shanghai Jiaotong Univer
Abstract
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.
AI and Society
KFUPM King Fahd Univeris
Abstract
Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI values. This study investigates how closely LLMs' value preferences align with those of two human groups: a US-representative sample and AI practitioners. We evaluate 23 LLMs across four tasks: (T1) selecting key responsible AI values, (T2) rating their importance in specific contexts, (T3) resolving trade-offs between competing values, and (T4) prioritizing software requirements that embody those values. The results show that LLMs generally align more closely with AI practitioners than with the US-representative sample, emphasizing fairness, privacy, transparency, safety, and accountability. However, inconsistencies appear between the values that LLMs claim to uphold (Tasks 1-3) and the way they prioritize requirements (Task 4), revealing gaps in faithfulness between stated and applied behavior. These findings highlight the practical risk of relying on LLMs in requirements engineering without human oversight and motivate the need for systematic approaches to benchmark, interpret, and monitor value alignment in AI-assisted software development.
Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI values. This study investigates how closely LLMs' value preferences align with those of two human groups: a US-representative sample and AI practitioners. We evaluate 23 LLMs across four tasks: (T1) selecting key responsible AI values, (T2) rating their importance in specific contexts, (T3) resolving trade-offs between competing values, and (T4) prioritizing software requirements that embody those values. The results show that LLMs generally align more closely with AI practitioners than with the US-representative sample, emphasizing fairness, privacy, transparency, safety, and accountability. However, inconsistencies appear between the values that LLMs claim to uphold (Tasks 1-3) and the way they prioritize requirements (Task 4), revealing gaps in faithfulness between stated and applied behavior. These findings highlight the practical risk of relying on LLMs in requirements engineering without human oversight and motivate the need for systematic approaches to benchmark, interpret, and monitor value alignment in AI-assisted software development.
The University of Tokyo
Abstract
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr. AI Scientist, a state-of-the-art autonomous AI scientist system that mimics the core research workflow of a novice student researcher: Given the baseline paper from the human mentor, it analyzes its limitations, formulates novel hypotheses for improvement, validates them through rigorous experimentation, and writes a paper with the results. Unlike previous approaches that assume full automation or operate on small-scale code, Jr. AI Scientist follows a well-defined research workflow and leverages modern coding agents to handle complex, multi-file implementations, leading to scientifically valuable contributions. For evaluation, we conducted automated assessments using AI Reviewers, author-led evaluations, and submissions to Agents4Science, a venue dedicated to AI-driven scientific contributions. The findings demonstrate that Jr. AI Scientist generates papers receiving higher review scores than existing fully automated systems. Nevertheless, we identify important limitations from both the author evaluation and the Agents4Science reviews, indicating the potential risks of directly applying current AI Scientist systems and key challenges for future research. Finally, we comprehensively report various risks identified during development. We hope these insights will deepen understanding of current progress and risks in AI Scientist development.
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr. AI Scientist, a state-of-the-art autonomous AI scientist system that mimics the core research workflow of a novice student researcher: Given the baseline paper from the human mentor, it analyzes its limitations, formulates novel hypotheses for improvement, validates them through rigorous experimentation, and writes a paper with the results. Unlike previous approaches that assume full automation or operate on small-scale code, Jr. AI Scientist follows a well-defined research workflow and leverages modern coding agents to handle complex, multi-file implementations, leading to scientifically valuable contributions. For evaluation, we conducted automated assessments using AI Reviewers, author-led evaluations, and submissions to Agents4Science, a venue dedicated to AI-driven scientific contributions. The findings demonstrate that Jr. AI Scientist generates papers receiving higher review scores than existing fully automated systems. Nevertheless, we identify important limitations from both the author evaluation and the Agents4Science reviews, indicating the potential risks of directly applying current AI Scientist systems and key challenges for future research. Finally, we comprehensively report various risks identified during development. We hope these insights will deepen understanding of current progress and risks in AI Scientist development.
Research Automation with AI
Edison Scientific Inc, 1
Abstract
Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.
Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.
AGI: Artificial General Intelligence
Abstract
Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and operational data under tight time constraints. We present Geothermal Analytics and Intelligent Agent, or GAIA, an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA Digital Twin, or DT, which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA's specialized capability for handling complex geothermal-related tasks, we curate a benchmark test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system's performance. We envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.
Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and operational data under tight time constraints. We present Geothermal Analytics and Intelligent Agent, or GAIA, an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA Digital Twin, or DT, which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA's specialized capability for handling complex geothermal-related tasks, we curate a benchmark test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system's performance. We envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.
Deep Learning
City St Georges, Univer
Abstract
Artificial Intelligence (AI) is a powerful new language of science as evidenced by recent Nobel Prizes in chemistry and physics that recognized contributions to AI applied to those areas. Yet, this new language lacks semantics, which makes AI's scientific discoveries unsatisfactory at best. With the purpose of uncovering new facts but also improving our understanding of the world, AI-based science requires formalization through a framework capable of translating insight into comprehensible scientific knowledge. In this paper, we argue that logic offers an adequate framework. In particular, we use logic in a neurosymbolic framework to offer a much needed semantics for deep learning, the neural network-based technology of current AI. Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied. Instead, there is a plethora of encoding and knowledge extraction approaches designed for particular cases. To rectify this, we introduced a framework for semantic encoding, making explicit the mapping between neural networks and logic, and characterizing the common ingredients of the various existing approaches. In this paper, we describe succinctly and exemplify how logical semantics and neural networks are linked through this framework, we review some of the most prominent approaches and techniques developed for neural encoding and knowledge extraction, provide a formal definition of our framework, and discuss some of the difficulties of identifying a semantic encoding in practice in light of analogous problems in the philosophy of mind.
Artificial Intelligence (AI) is a powerful new language of science as evidenced by recent Nobel Prizes in chemistry and physics that recognized contributions to AI applied to those areas. Yet, this new language lacks semantics, which makes AI's scientific discoveries unsatisfactory at best. With the purpose of uncovering new facts but also improving our understanding of the world, AI-based science requires formalization through a framework capable of translating insight into comprehensible scientific knowledge. In this paper, we argue that logic offers an adequate framework. In particular, we use logic in a neurosymbolic framework to offer a much needed semantics for deep learning, the neural network-based technology of current AI. Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied. Instead, there is a plethora of encoding and knowledge extraction approaches designed for particular cases. To rectify this, we introduced a framework for semantic encoding, making explicit the mapping between neural networks and logic, and characterizing the common ingredients of the various existing approaches. In this paper, we describe succinctly and exemplify how logical semantics and neural networks are linked through this framework, we review some of the most prominent approaches and techniques developed for neural encoding and knowledge extraction, provide a formal definition of our framework, and discuss some of the difficulties of identifying a semantic encoding in practice in light of analogous problems in the philosophy of mind.
VISTAMILK, Dublin City Un
Abstract
Grasslands, constituting the world's second-largest terrestrial carbon sink, play a crucial role in biodiversity and the regulation of the carbon cycle. Currently, the Irish dairy sector, a significant economic contributor, grapples with challenges related to profitability and sustainability. Presently, grass growth forecasting relies on impractical mechanistic models. In response, we propose deep learning models tailored for univariate datasets, presenting cost-effective alternatives. Notably, a temporal convolutional network designed for forecasting Perennial Ryegrass growth in Cork exhibits high performance, leveraging historical grass height data with RMSE of 2.74 and MAE of 3.46. Validation across a comprehensive dataset spanning 1,757 weeks over 34 years provides insights into optimal model configurations. This study enhances our understanding of model behavior, thereby improving reliability in grass growth forecasting and contributing to the advancement of sustainable dairy farming practices.
Grasslands, constituting the world's second-largest terrestrial carbon sink, play a crucial role in biodiversity and the regulation of the carbon cycle. Currently, the Irish dairy sector, a significant economic contributor, grapples with challenges related to profitability and sustainability. Presently, grass growth forecasting relies on impractical mechanistic models. In response, we propose deep learning models tailored for univariate datasets, presenting cost-effective alternatives. Notably, a temporal convolutional network designed for forecasting Perennial Ryegrass growth in Cork exhibits high performance, leveraging historical grass height data with RMSE of 2.74 and MAE of 3.46. Validation across a comprehensive dataset spanning 1,757 weeks over 34 years provides insights into optimal model configurations. This study enhances our understanding of model behavior, thereby improving reliability in grass growth forecasting and contributing to the advancement of sustainable dairy farming practices.
Interests not found
We did not find any papers that match the below interests.
Try other terms also consider if the content exists in arxiv.org.
- NoSQL Databases
You can edit or add more interests any time.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback