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

arXiv:2607.06223 · cs.AI · Submitted 2026-07-07 · Read on arXiv

cs.AI

Submitted: 2026-07-07

Updated: 2026-10-07

Code: https://github.com/e3trange/IGRPO

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Information Gain — 3× in this paper · explained in 2 episodes
• Information Gain-based Rollout Policy Optimization — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Agentic Entropy-Balanced Policy Optimization
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Deep Research Agents: A Systematic Examination And Roadmap
• Qwen2.5 Technical Report
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• ZeroSearch: Incentivize the Search Capability of LLMs without Searching
• LLaMA: Open and Efficient Foundation Language Models
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Group Sequence Policy Optimization

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems