5 papers
Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents
Ruochen Zhou, Zhengyu Chen, Luan Zhang +3
Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory. Our trajectory-level analysis…
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Luan Zhang, Ruochen Zhou, Dandan Song +9
Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has…
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
Zhengyu Chen, Teng Xiao, Huaisheng Zhu +3
Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research trajectories are generated, eval…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…
Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization
Zhengyu Chen, Jinluan Yang, Teng Xiao +6
Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforce…