Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of intermediate decisions before receiving a final outcome. However, existing methods still face a key limitation: the rollout budget is often allocated without explicitly assessing the utility of intermediate states. As a result, substantial computation may be spent on low-value states, even though different branches can vary drastically in their informativeness. In this paper, we propose Information Gain-based Rollout Policy

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

  • PossiblePossibly related (embedding) · 47%rllm-org/rllm
  • LinkedLinked via arxiv author · 85%Yijun Zhang

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

  • LinkedLinked via arxiv author · 85%Tianfan Xue

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

  • LinkedLinked via arxiv author · 85%Jiaxin Ding

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

  • LinkedLinked via arxiv author · 85%Yule Xie

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

  • LinkedLinked via arxiv author · 85%Shiqing Gao

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

  • LinkedLinked via arxiv author · 85%Haoxiang Zhang

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agen

Implements

Covers

authored (incoming)

Covers (incoming)

Implements (incoming)

Related across the graph

Topics