5 papers
Can RL Improve Generalization of LLM Agents? An Empirical Study
Zhiheng Xi, Xin Guo, Jiaqi Liu +11
Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations re…
Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
Xin Guo, Zhiheng Xi, Yiwen Ding +6
Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models (LVLMs), where models explore and learn from successf…
MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use
Weikang Zhao, Xili Wang, Chengdi Ma +6
With the recent rapid advancement of Agentic Intelligence, agentic tool use in LLMs has become increasingly important. During multi-turn interactions between agents and users, the…
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Zhiheng Xi, Dingwen Yang, Jixuan Huang +21
Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as scie…
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
Yiwen Ding, Zhiheng Xi, Wei He +7
Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effect…