RTMC: Step-Level Credit Assignment via Rollout Trees

arXiv:2604.11037v1 Announce Type: cross Abstract: Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned value networks introduce notable overhead and can be fragile under sparse rewards. We observe that group rollouts targeting the same problem often traverse overlapping intermediate states, implicitly forming a tree whose branches diverge at successive decision points. Building on this insight, we introduce Rollout-Tree Monte Carlo (RTMC) advantage estimation, which aggregates return statistics across rollouts sharing a common state to produce per-step Q-values and advantages--without any learned critic. A state-action signature system compresses raw interaction histories into compact, comparable representations, making cross-rollout state matching tractable. On SWE-bench Verified, RTMC improves pass@1 by 3.2 percentage points over GRPO.

Related

• Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
• Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
• Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
• Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Source: arXiv cs.AI | 2026-04-14