10 papers
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
Tongxu Luo, Rongsheng Wang, Jiaxi Bi +22
Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional cod…
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
Jiaxi Bi, Tongxu Luo, Wenyu Du +2
Parallel reasoning enhances Large Reasoning Models (LRMs) but incurs prohibitive costs due to futile paths caused by early errors. To mitigate this, path pruning at the prefix leve…
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…
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…
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…
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…