Hong Kong University of Science and Technology HKUST
AI Insights
- Data quality issues: LLMs can perpetuate biases and inaccuracies present in training data. (ML: 0.99)
- As the use of LLMs becomes more widespread, it is essential to address concerns around data quality, bias, and transparency. (ML: 0.99)
- The use of Large Language Models (LLMs) is becoming increasingly prevalent in data analysis and visualization. (ML: 0.98)
- Ontology Matching: The process of matching concepts from different ontologies (formal representations of knowledge) to establish relationships between them. (ML: 0.97)
- Several studies have demonstrated the effectiveness of LLM-based agents in automating tasks such as data visualization, chart generation, and question answering. (ML: 0.95)
- Large Language Models (LLMs): A type of artificial intelligence model that can process and understand human language to generate text or perform other tasks. (ML: 0.95)
- Researchers are exploring various applications of LLMs, including data cleaning, data standardization, ontology matching, query rewriting, and database knob tuning. (ML: 0.95)
- Data+ AI Ecosystems: An integrated system that combines data storage, processing, and analysis with artificial intelligence capabilities. (ML: 0.95)
- The integration of LLMs into data analysis and visualization is a rapidly evolving field with significant potential for innovation and improvement. (ML: 0.94)
- Further research is needed to fully understand the capabilities and limitations of LLM-based agents in various applications. (ML: 0.93)
Abstract
Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term "data agent" is currently used inconsistently, conflating simple query responsive assistants with aspirational fully autonomous "data scientists". This ambiguity blurs capability boundaries and accountability, making it difficult for users, system builders, and regulators to reason about what a "data agent" can and cannot do. In this tutorial, we propose the first hierarchical taxonomy of data agents from Level 0 (L0, no autonomy) to Level 5 (L5, full autonomy). Building on this taxonomy, we will introduce a lifecycleand level-driven view of data agents. We will (1) present the L0-L5 taxonomy and the key evolutionary leaps that separate simple assistants from truly autonomous data agents, (2) review representative L0-L2 systems across data management, preparation, and analysis, (3) highlight emerging Proto-L3 systems that strive to autonomously orchestrate end-to-end data workflows to tackle diverse and comprehensive data-related tasks under supervision, and (4) discuss forward-looking research challenges towards proactive (L4) and generative (L5) data agents. We aim to offer both a practical map of today's systems and a research roadmap for the next decade of data-agent development.
Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term "data agent" is currently used inconsistently, conflating simple query responsive assistants with aspirational fully autonomous "data scientists". This ambiguity blurs capability boundaries and accountability, making it difficult for users, system builders, and regulators to reason about what a "data agent" can and cannot do. In this tutorial, we propose the first hierarchical taxonomy of data agents from Level 0 (L0, no autonomy) to Level 5 (L5, full autonomy). Building on this taxonomy, we will introduce a lifecycleand level-driven view of data agents. We will (1) present the L0-L5 taxonomy and the key evolutionary leaps that separate simple assistants from truly autonomous data agents, (2) review representative L0-L2 systems across data management, preparation, and analysis, (3) highlight emerging Proto-L3 systems that strive to autonomously orchestrate end-to-end data workflows to tackle diverse and comprehensive data-related tasks under supervision, and (4) discuss forward-looking research challenges towards proactive (L4) and generative (L5) data agents. We aim to offer both a practical map of today's systems and a research roadmap for the next decade of data-agent development.
Why we are recommending this paper?
Due to your Interest in Managing teams of data scientists
This paper explores the emerging field of data agents, leveraging large language models for automated data management – a crucial area for managing data science teams and workflows. Understanding this paradigm is essential for strategically implementing AI solutions within your data science operations.
Due to your Interest in Managing teams of data scientists
This paper explores the emerging field of data agents, leveraging large language models for automated data management – a crucial area for managing data science teams and workflows. Understanding this paradigm is essential for strategically implementing AI solutions within your data science operations.
Amazon
AI Insights
- One potential weakness of this approach is that it may be limited by the availability of high-quality training data and the complexity of the problems being addressed. (ML: 0.98)
- With AI, this process becomes even more efficient and accurate. (ML: 0.98)
- Imagine you're trying to solve a complex math problem, but you're not sure where to start. (ML: 0.95)
- The use of AI in formal mathematical reasoning has opened up new possibilities for solving complex problems and making accurate predictions. (ML: 0.93)
- Formal mathematical reasoning has been increasingly used in various fields, including computer science, mathematics, and artificial intelligence. (ML: 0.93)
- Formal mathematical reasoning is like having a super-smart assistant that can help you break down the problem into smaller parts and find the solution. (ML: 0.92)
- The main idea is to explore the intersection of formal mathematical reasoning and AI, highlighting its potential applications and benefits. (ML: 0.88)
- The paper discusses the development and application of formal mathematical reasoning using AI. (ML: 0.88)
Abstract
We introduce CSLib, an open-source framework for proving computer-science-related theorems and writing formally verified code in the Lean proof assistant. CSLib aims to be for computer science what Lean's Mathlib is for mathematics. Mathlib has been tremendously impactful: it is a key reason for Lean's popularity within the mathematics research community, and it has also played a critical role in the training of AI systems for mathematical reasoning. However, the base of computer science knowledge in Lean is currently quite limited. CSLib will vastly enhance this knowledge base and provide infrastructure for using this knowledge in real-world verification projects. By doing so, CSLib will (1) enable the broad use of Lean in computer science education and research, and (2) facilitate the manual and AI-aided engineering of large-scale formally verified systems.
We introduce CSLib, an open-source framework for proving computer-science-related theorems and writing formally verified code in the Lean proof assistant. CSLib aims to be for computer science what Lean's Mathlib is for mathematics. Mathlib has been tremendously impactful: it is a key reason for Lean's popularity within the mathematics research community, and it has also played a critical role in the training of AI systems for mathematical reasoning. However, the base of computer science knowledge in Lean is currently quite limited. CSLib will vastly enhance this knowledge base and provide infrastructure for using this knowledge in real-world verification projects. By doing so, CSLib will (1) enable the broad use of Lean in computer science education and research, and (2) facilitate the manual and AI-aided engineering of large-scale formally verified systems.
Why we are recommending this paper?
Due to your Interest in Data Science Management
Coming from Amazon, this paper introduces CSLib, a framework for formally verified code – a valuable tool for ensuring the reliability and correctness of software engineering processes, aligning with your interest in engineering management.
Due to your Interest in Data Science Management
Coming from Amazon, this paper introduces CSLib, a framework for formally verified code – a valuable tool for ensuring the reliability and correctness of software engineering processes, aligning with your interest in engineering management.
California State University, San Marcos
AI Insights
- The authors conclude that maintaining heterogeneity in SE research is crucial for the field's progress and innovation. (ML: 0.99)
- The authors do not provide a clear solution for implementing heterogeneity in SE research. (ML: 0.99)
- This shift is causing researchers to prioritize safe and incremental contributions over disruptive innovations. (ML: 0.98)
- The authors propose maintaining heterogeneity in the organization of SE research by allowing both funded and hands-on research models to coexist. (ML: 0.98)
- Heterogeneity: The presence of different approaches, methods, or models within a field or discipline. (ML: 0.97)
- They propose that researchers should be allowed to choose between funded and hands-on research models, depending on their goals and preferences. (ML: 0.96)
- The authors argue that the shift towards a funded research model in software engineering is leading to the extinction of hands-on research methods, such as action research. (ML: 0.94)
- Hands-On Research Model: A research approach that involves direct involvement and participation in the research process. (ML: 0.94)
- They acknowledge that the shift towards a funded research model may be difficult to reverse. (ML: 0.92)
- Funded Research Model: A research approach where funding is provided for specific projects or proposals. (ML: 0.86)
Abstract
The heterogeneity in the organization of software engineering (SE) research historically exists, i.e., funded research model and hands-on model, which makes software engineering become a thriving interdisciplinary field in the last 50 years. However, the funded research model is becoming dominant in SE research recently, indicating such heterogeneity has been seriously and systematically threatened. In this essay, we first explain why the heterogeneity is needed in the organization of SE research, then present the current trend of SE research nowadays, as well as the consequences and potential futures. The choice is at our hands, and we urge our community to seriously consider maintaining the heterogeneity in the organization of software engineering research.
The heterogeneity in the organization of software engineering (SE) research historically exists, i.e., funded research model and hands-on model, which makes software engineering become a thriving interdisciplinary field in the last 50 years. However, the funded research model is becoming dominant in SE research recently, indicating such heterogeneity has been seriously and systematically threatened. In this essay, we first explain why the heterogeneity is needed in the organization of SE research, then present the current trend of SE research nowadays, as well as the consequences and potential futures. The choice is at our hands, and we urge our community to seriously consider maintaining the heterogeneity in the organization of software engineering research.
Why we are recommending this paper?
Due to your Interest in Managing teams of data scientists
This research addresses the diverse models within software engineering, offering insights into managing different approaches to research and development, which is directly relevant to your interest in managing teams.
Due to your Interest in Managing teams of data scientists
This research addresses the diverse models within software engineering, offering insights into managing different approaches to research and development, which is directly relevant to your interest in managing teams.
Maastricht University
AI Insights
- The text also discusses the relationship between groundedness and maximization of complete and transitive preference relations. (ML: 0.97)
- Some of the key concepts explored include consistency, monotonicity, and weak axiom of revealed preference (WARP). (ML: 0.97)
- The results have implications for understanding rationalizability and groundedness in choice theory. (ML: 0.95)
- GAIC: Grounded Axiom of Revealed Preference. (ML: 0.92)
- A choice function c is said to satisfy GMAIC if it maximizes a complete and transitive preference relation over non-empty subsets of X. (ML: 0.91)
- Groundedness: A choice function c satisfies groundedness if for all x ∈ X, there exists a set S ⊆ X \{x such that I(S) = ∅. (ML: 0.89)
- GMAIC: Grounded Maximizing Axiom of Choice. (ML: 0.89)
- The provided text provides a comprehensive proof of various theorems and propositions related to choice theory. (ML: 0.89)
- The proofs cover topics such as injectivity, surjectivity, and double union closure of interpretation functions. (ML: 0.88)
- A choice function c is said to satisfy GAIC if it satisfies groundedness and the corresponding interpretation I satisfies consistency, monotonicity, and WARP. (ML: 0.88)
- The proofs demonstrate the relationship between different axioms and properties of choice functions. (ML: 0.86)
- The provided text appears to be a proof of various theorems and propositions related to choice theory, specifically in the context of rationalizability and groundedness. (ML: 0.86)
Abstract
This paper proposes a model of choice via agentic artificial intelligence (AI). A key feature is that the AI may misinterpret a menu before recommending what to choose. A single acyclicity condition guarantees that there is a monotonic interpretation and a strict preference relation that together rationalize the AI's recommendations. Since this preference is in general not unique, there is no safeguard against it misaligning with that of a decision maker. What enables the verification of such AI alignment is interpretations satisfying double monotonicity. Indeed, double monotonicity ensures full identifiability and internal consistency. But, an additional idempotence property is required to guarantee that recommendations are fully rational and remain grounded within the original feasible set.
This paper proposes a model of choice via agentic artificial intelligence (AI). A key feature is that the AI may misinterpret a menu before recommending what to choose. A single acyclicity condition guarantees that there is a monotonic interpretation and a strict preference relation that together rationalize the AI's recommendations. Since this preference is in general not unique, there is no safeguard against it misaligning with that of a decision maker. What enables the verification of such AI alignment is interpretations satisfying double monotonicity. Indeed, double monotonicity ensures full identifiability and internal consistency. But, an additional idempotence property is required to guarantee that recommendations are fully rational and remain grounded within the original feasible set.
Why we are recommending this paper?
Due to your Interest in AI for Data Science Management
This paper proposes a model of choice via AI, exploring the potential of AI systems in decision-making processes – a key area for optimizing workflows and strategies within your data science teams.
Due to your Interest in AI for Data Science Management
This paper proposes a model of choice via AI, exploring the potential of AI systems in decision-making processes – a key area for optimizing workflows and strategies within your data science teams.
Cornell University
AI Insights
- Biased sample: The participants may have been self-selected or biased towards being more aware of accessibility issues. (ML: 0.98)
- Non-disabled team members faced challenges in determining when and how to offer help without overstepping. (ML: 0.97)
- Participants described navigating unfamiliar norms, adapting their behavior, and becoming more attentive and responsive team members. (ML: 0.96)
- Non-disabled team members developed allyship through an ongoing learning process. (ML: 0.96)
- Limited scope: The study focuses on virtual collaboration and may not be generalizable to other contexts. (ML: 0.96)
- Accessibility practices support allyship and relationships between team members. (ML: 0.93)
- Accessibility practices support relationships between team members by promoting equal access and fostering a culture of inclusion. (ML: 0.92)
- Allyship: the practice of supporting and advocating for disabled team members Accessibility practices: strategies and behaviors that promote equal access to collaboration and communication for all team members Participants described developing allyship through ongoing learning, adaptation, and responsiveness. (ML: 0.92)
Abstract
Virtual collaboration has transformed how people in mixed-ability teams, composed of disabled and non-disabled people, work together by offering greater flexibility. In these settings, accessibility practices, such as accommodations and inclusive norms, are essential for providing access to disabled people. However, we do not yet know how these practices shape broader facets of teamwork, such as productivity, participation, and camaraderie. To address this gap, we interviewed 18 participants (12 disabled, 6 non-disabled) who are part of mixed-ability teams. We found that beyond providing access, accessibility practices shaped how all participants coordinated tasks, sustained rapport, and negotiated responsibilities. Accessibility practices also introduced camaraderie challenges, such as balancing empathy and accountability. Non-disabled participants described allyship as a learning process and skill shaped by their disabled team members and team culture. Based on our findings, we present recommendations for team practices and design opportunities for virtual collaboration tools that reframe accessibility practices as a foundation for strong teamwork.
Virtual collaboration has transformed how people in mixed-ability teams, composed of disabled and non-disabled people, work together by offering greater flexibility. In these settings, accessibility practices, such as accommodations and inclusive norms, are essential for providing access to disabled people. However, we do not yet know how these practices shape broader facets of teamwork, such as productivity, participation, and camaraderie. To address this gap, we interviewed 18 participants (12 disabled, 6 non-disabled) who are part of mixed-ability teams. We found that beyond providing access, accessibility practices shaped how all participants coordinated tasks, sustained rapport, and negotiated responsibilities. Accessibility practices also introduced camaraderie challenges, such as balancing empathy and accountability. Non-disabled participants described allyship as a learning process and skill shaped by their disabled team members and team culture. Based on our findings, we present recommendations for team practices and design opportunities for virtual collaboration tools that reframe accessibility practices as a foundation for strong teamwork.
Why we are recommending this paper?
Due to your Interest in Managing tech teams
This research investigates the impact of accessibility practices on teamwork, particularly in virtual environments – a critical consideration for inclusive and effective collaboration within diverse data science teams.
Due to your Interest in Managing tech teams
This research investigates the impact of accessibility practices on teamwork, particularly in virtual environments – a critical consideration for inclusive and effective collaboration within diverse data science teams.
Renmin University of China
AI Insights
- SWE-Master: A framework for software engineering tasks that combines a strong policy with a robust selection mechanism. (ML: 0.95)
- Test-Time Scaling is a crucial component in unlocking peak performance for software engineering tasks. (ML: 0.95)
- The SWE-Master framework may not be suitable for all types of software engineering tasks due to its reliance on large-scale language models. (ML: 0.95)
- RL (Reinforcement Learning): A type of machine learning where an agent learns to take actions in an environment to maximize a reward signal. (ML: 0.94)
- SFT (Simulated Function Transfer): A method for training models by simulating the behavior of other models and transferring their knowledge. (ML: 0.92)
- The use of reinforcement learning in software engineering has been explored in previous studies, but the SWE-Master framework presents a novel approach by combining RL with simulated function transfer and test-time scaling. (ML: 0.91)
- The SWE-Master framework effectively unleashes the potential of large-scale language models, achieving high efficacy without relying on excessive model scaling. (ML: 0.90)
- The transition from SFT to RL consistently yields notable performance gains across different model scales, validating the robustness of our RL framework. (ML: 0.87)
- The SWE-Master framework demonstrates superior performance compared to existing open-source code agents, achieving a resolve rate of 61.4% at Pass@1. (ML: 0.74)
- Incorporating Test-Time Scaling via the simulated verification and ranking mechanism using SWE-World yields substantial improvements in resolve rates. (ML: 0.69)
Abstract
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.
Why we are recommending this paper?
Due to your Interest in Engineering Management
Due to your Interest in Engineering Management
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.
- Data Science Engineering Management
- AI for Data Science Engineering
- Data Science Engineering
You can edit or add more interests any time.
💬 Help Shape Our Pricing
We're exploring pricing options to make this project sustainable. Take 3 minutes to share what you'd be willing to pay (if anything). Your input guides our future investment.
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