3 papers
cs.AI2026
Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents
Wenjie Liao, Liangjie Zhao, Zehong Cao
Self-evolving tool-integrated agents learn from tasks and feedback generated within their own training loop. A Curriculum Agent generates tasks, while an Executor Agent learns from…
cs.AI2026
UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning
Wenjie Liao, Liangjie Zhao, Zehong Cao
Self-evolving methods reduce the need for human-annotated trajectories by allowing tool-using agents to generate their own training data. Yet existing methods typically separate tr…
cs.LG2026
IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning
Wenjie Liao, Like Wu, Liangjie Zhao +2
Self-play fine-tuning enables large language models to improve beyond supervised fine-tuning without additional human annotations by contrasting annotated responses with self-gener…