5 papers
DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance
Yansi Li, Zhuosheng Zhang
Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we…
Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
Zheng Wu, Xingyu Lou, Xinbei Ma +5
Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks w…
Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
Haodong Zhao, Chenyan Zhao, Yansi Li +2
The capacity of Large Language Models (LLMs) to reason is fundamental to their application in complex, knowledge-intensive domains. In real-world scenarios, LLMs are often augmente…
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He +10
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Yansi Li, Jiahao Xu, Tian Liang +8
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Tradi…