FIELD NOTES TOPIC
information gain
1 note, newest first.
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
The paper proposes a new method called Information Gain-based Rollout Policy Optimization (IGRPO) for improving large language model (LLM) agents in long-horizon search tasks. The method addresses the issue of existing…
