Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners

The recent introduction of DESIGNER, a design-logic-guided reasoning data synthesis pipeline, aims to enhance the capabilities of large language models (LLMs) in tackling complex, multidisciplinary questions. By leveraging extensive raw documents, DESIGNER generates high-difficulty questions that challenge LLMs' reasoning abilities across various disciplines.

The SkeletonAgent framework has been introduced to enhance skeleton-based action recognition by integrating Large Language Models (LLMs) with a recognition model through two cooperative agents, the Questioner and Selector. This innovative approach aims to improve the accuracy of distinguishing similar actions by providing targeted guidance and feedback between the LLM and the recognition model.

Recent advancements in 3D scene-language understanding have led to the development of the 3D Spatial Language Instruction Mask (3D-SLIM), which enhances the reasoning capabilities of Large Language Models (LLMs) by replacing traditional causal attention masks with adaptive attention masks tailored to the spatial structures of 3D scenes. This innovation addresses key limitations in current methodologies, such as sequential bias and restricted attention in task-specific reasoning.

The introduction of InEx presents a novel approach to mitigating hallucinations in large language models (LLMs) by employing a training-free, multi-agent framework that incorporates introspective reasoning and cross-modal collaboration. This method aims to enhance the reliability of multimodal LLMs (MLLMs) by autonomously refining responses through iterative verification processes.

A systematic survey on Deep Research (DR) has been published, highlighting the evolution of large language models (LLMs) from mere text generators to sophisticated problem solvers. This survey outlines a three-stage roadmap for integrating LLMs with external tools, enabling them to tackle complex tasks that require critical thinking and multi-source verification.

A new framework named UniFact has been introduced to unify Hallucination Detection (HD) and Fact Verification (FV) for Large Language Models (LLMs), addressing the prevalent issue of LLMs generating factually incorrect content, known as hallucinations. This initiative aims to bridge the gap between two previously isolated research paradigms, enhancing the evaluation of LLM outputs.

A new benchmark dataset, TCM-BEST4SDT, has been proposed to evaluate the capabilities of Large Language Models (LLMs) in the context of Traditional Chinese Medicine (TCM), specifically focusing on Syndrome Differentiation and Treatment (SDT). This dataset aims to address the challenges posed by TCM's individualized and holistic nature, which current evaluation frameworks often overlook.

A new study introduces Stable Rank Group Relative Policy Optimization (SR-GRPO), which utilizes stable rank as an intrinsic quality signal for aligning Large Language Models (LLMs) with human preferences, addressing limitations of traditional methods that rely on external supervision. The stable rank measures the effective dimensionality of hidden states, achieving notable improvements in task accuracy.