Abstract
Scientific inquiry requires systems-level reasoning that integrates heterogeneous experimental data, cross-domain knowledge, and mechanistic evidence into coherent explanations. While Large Language Models (LLMs) offer inferential capabilities, they often depend on retrieval-augmented contexts that lack structural depth. Traditional Knowledge Graphs (KGs) attempt to bridge this gap, yet their pairwise constraints fail to capture the irreducible higher-order interactions that govern emergent physical behavior. To address this, we introduce a methodology for constructing hypergraph-based knowledge representations that faithfully encode multi-entity relationships. Applied to a corpus of ~1,100 manuscripts on biocomposite scaffolds, our framework constructs a global hypergraph of 161,172 nodes and 320,201 hyperedges, revealing a scale-free topology (power law exponent ~1.23) organized around highly connected conceptual hubs. This representation prevents the combinatorial explosion typical of pairwise expansions and explicitly preserves the co-occurrence context of scientific formulations. We further demonstrate that equipping agentic systems with hypergraph traversal tools, specifically using node-intersection constraints, enables them to bridge semantically distant concepts. By exploiting these higher-order pathways, the system successfully generates grounded mechanistic hypotheses for novel composite materials, such as linking cerium oxide to PCL scaffolds via chitosan intermediates. This work establishes a "teacherless" agentic reasoning system where hypergraph topology acts as a verifiable guardrail, accelerating scientific discovery by uncovering relationships obscured by traditional graph methods.

Why we are recommending this paper?
Due to your Interest in Knowledge Graphs

This paper from MIT explores knowledge representation, aligning with your interest in knowledge graphs and taxonomy of products. It investigates how systems can integrate diverse knowledge for scientific reasoning, a key area of your focus.

Abstract
As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved information has gone unexamined. We address this gap with a novel framework to investigate how source preferences affect LLM resolution of inter-context knowledge conflicts in English, motivated by interdisciplinary research on credibility. With a comprehensive, tightly-controlled evaluation of 13 open-weight LLMs, we find that LLMs prefer institutionally-corroborated information (e.g., government or newspaper sources) over information from people and social media. However, these source preferences can be reversed by simply repeating information from less credible sources. To mitigate repetition effects and maintain consistent preferences, we propose a novel method that reduces repetition bias by up to 99.8%, while also maintaining at least 88.8% of original preferences. We release all data and code to encourage future work on credibility and source preferences in knowledge-intensive NLP.

Why we are recommending this paper?
Due to your Interest in Knowledge Management

Given your interest in knowledge graphs and how they are used, this Heidelberg University paper directly addresses the source selection process within LLMs. Understanding how LLMs prioritize information is crucial for effective knowledge management.

Abstract
We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when learning multiple tasks sequentially. This method referred to as Group and Exclusive Sparsity based Continual Learning (GESCL) avoids forgetting of previous tasks by ensuring the stability of the CNN via a stability regularization term, which prevents filters detected as important for past tasks to deviate too much when learning a new task. On top of that, GESCL makes the network plastic via a plasticity regularization term that leverage the over-parameterization of CNNs to efficiently sparsify the network and tunes unimportant filters making them relevant for future tasks. Doing so, GESCL deals with significantly less parameters and computation compared to CL approaches that either dynamically expand the network or memorize past tasks' data. Experiments on popular CL vision benchmarks show that GESCL leads to significant improvements over state-of-the-art method in terms of overall CL performance, as measured by classification accuracy as well as in terms of avoiding catastrophic forgetting.

Why we are recommending this paper?
Due to your Interest in Continual Generalized Category Discovery

This paper from Bochum University of Applied Science tackles continual learning, a relevant area for your interest in product categorization and knowledge graphs. It offers a method for adapting models to new data, aligning with your need for generalized category discovery.

Abstract
Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this domain; however, they typically rely on key-value pairing, which can introduce inter-task interference and hinder scalability. To overcome these limitations, we propose a novel approach employing task-specific Prompt-Prototype (ProP), thereby eliminating the need for key-value pairs. In our method, task-specific prompts facilitate more effective feature learning for the current task, while corresponding prototypes capture the representative features of the input. During inference, predictions are generated by binding each task-specific prompt with its associated prototype. Additionally, we introduce regularization constraints during prompt initialization to penalize excessively large values, thereby enhancing stability. Experiments on several widely used datasets demonstrate the effectiveness of the proposed method. In contrast to mainstream prompt-based approaches, our framework removes the dependency on key-value pairs, offering a fresh perspective for future continual learning research.

Why we are recommending this paper?
Due to your Interest in Continual Generalized Category Discovery

This paper from Dalian University of Technology focuses on continual learning techniques, directly addressing your interest in product categorization and knowledge management. The key-value free approach is particularly relevant for scalable knowledge graph construction.

Abstract
Let $H$ be a fixed graph whose edges are colored red and blue and let $β\in [0,1]$. Let $I(H, β)$ be the (asymptotically normalized) maximum number of copies of $H$ in a large red/blue edge-colored complete graph $G$, where the density of red edges in $G$ is $β$. This refines the problem of determining the semi-inducibility of $H$, which is itself a generalization of the classical question of determining the inducibility of $H$. The function $I(H, β)$ for $β\in [0,1]$ was not known for any graph $H$ on more than three vertices, except when $H$ is a monochromatic clique (Kruskal-Katona) or a monochromatic star (Reiher-Wagner). We obtain sharp results for some four and five vertex graphs, addressing several recent questions posed by various authors. We also obtain some general results for trees and stars. Many open problems remain.

Why we are recommending this paper?
Due to your Interest in Graphs for Products

This paper from the University of Illinois UrbanaChampaign investigates graph structures, a core component of your interest in knowledge graphs and ontology for products. Understanding graph inducibility is fundamental to building effective knowledge representations.