AgentRM: Enhancing Agent Generalization with Reward Modeling

AgentRM proposes a generalizable reward model to guide LLM-based agents during test-time search, outperforming direct policy fine-tuning. Three reward modeling strategies—explicit, implicit, and LLM-as-a-judge—are explored, and AgentRM improves base policy performance by an average of 8.8 points across nine tasks, surpassing top general agents by 4.0 points. It also shows strong weak-to-strong generalization and can boost specialized agents, with plans to release code for further research.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• reinforcement-learning
• fine-tuning