6 papers
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…
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…
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…
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…
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…
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…