5 papers
Harness-G: A Graph-Structured Harness for Search Agents
Yanning Hou, Haoyuan Chen, Sihang Zhou +7
Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. C…
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
Xirui Liu, Sihang Zhou, Yanning Hou +6
Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different tasks. However, these knowled…
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Hao-Yuan Chen
Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourth axis, granularity of externa…
Decoupled Travel Planning with Behavior Forest
Duanyang Yuan, Sihang Zhou, Yanning Hou +7
Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning s…
Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism
Xiaoshu Chen, Sihang Zhou, Ke Liang +5
Chain of thought (CoT) fine-tuning aims to endow large language models (LLMs) with reasoning capabilities by training them on curated reasoning traces. It leverages both supervised…