collaborators

6 papers

cs.AI2025

The Station: An Open-World Environment for AI-Driven Discovery

Stephen Chung, Wenyu Du

We introduce the STATION, an open-world multi-agent environment for autonomous scientific discovery. The Station simulates a complete scientific ecosystem, where agents can engage…

cs.CL2025

Learning from Peers in Reasoning Models

Tongxu Luo, Wenyu Du, Jiaxi Bi +5

Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process sta…

cs.CL2025

Thinker: Learning to Think Fast and Slow

Stephen Chung, Wenyu Du, Jie Fu

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in area…

cs.CL2025

Learning from Failures in Multi-Attempt Reinforcement Learning

Stephen Chung, Wenyu Du, Jie Fu

Recent advancements in reinforcement learning (RL) for large language models (LLMs), exemplified by DeepSeek R1, have shown that even a simple question-answering task can substanti…

cs.CL2025

Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking

Yifan Zhang, Wenyu Du, Dongming Jin +2

Chain-of-thought (CoT) significantly enhances the performance of large language models (LLMs) across a wide range of tasks, and prior research shows that CoT can theoretically incr…

cs.CL2025

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

Xu Wang, Yan Hu, Wenyu Du +3

Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth i…