8 papers
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu +11
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memo…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions
Boyan Duan, Xiao Liang, Shuai Lu +7
Automated theorem proving in Euclidean geometry, particularly for International Mathematical Olympiad (IMO) level problems, remains a major challenge and an important research focu…
AFM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
Qianben Chen, Jingyi Cao, Jiayu Zhang +12
Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, whic…
Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
Eric Hanchen Jiang, Mengting Li, Guancheng Wan +8
The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial…
Sequential Diffusion Language Models
Yangzhou Liu, Yue Cao, Hao Li +13
Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value (KV) caches. Block diffusion mitigat…
Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
Fanding Huang, Guanbo Huang, Xiao Fan +7
Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning is often framed as balancing exploration and exploitation in action space, typically operationalized with to…
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Xumeng Wen, Zihan Liu, Shun Zheng +9
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant int…