# Process Reward Informed Tree Rollout for Effective Multi-Turn RL

arXiv: https://arxiv.org/abs/2607.15610 · HTML: https://mlsanity.com/paper/2607.15610/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 17 of 17)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution](https://mlsanity.com/paper/2505.20732/) (2025)
- [Agentic Reinforcement Learning with Implicit Step Rewards](https://mlsanity.com/paper/2509.19199/) (2025)
- [SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph](https://mlsanity.com/paper/2510.20022/) (2025)
- [Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2510.24302/) (2025)
- [ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue](https://mlsanity.com/paper/2603.02216/) (2026)
- [TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents](https://mlsanity.com/paper/2602.11767/) (2026)

## Built on by (most cited first, 2 of 2)

- [SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL](https://mlsanity.com/paper/2609.34805/) (2026)
- [Understanding Enrichment in Reinforcement Learning](https://mlsanity.com/paper/2610.02846/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation. In long-horizon agentic tasks, such a uniform rollout strategy can waste budget on uninformative dead-end attempts, while promising intermediate states do not receive sufficient exploration. The multi-turn structure of agentic trajectories, with interleaved actions and observations, naturally supports organizing a trajectory group as a tree, where each turn serves as a decision point for exploration. This perspective reframes effective exploration as the problem of deciding where to branch. We propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL. PATR uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops degenerate paths to reduce wasted sampling. The resulting rollout groups remain compatible with standard policy optimization while providing more efficient exploration under the same training budget. We evaluate PATR on FrozenLake and the challenging SWE-Bench, which is largely unexplored by prior tree-rollout agent RL methods. Experiments show that PATR improves performance by up to +5.0 points on SWE-Bench and +9.3 points on FrozenLake, highlighting process-guided tree rollouts as an effective strategy for scalable multi-turn RL.