# Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents

arXiv: https://arxiv.org/abs/2609.33875 · HTML: https://mlsanity.com/paper/2609.33875/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 69 of its 90 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- LLM alignment / RLHF / preference optimisation / [Reward hacking and misspecification](https://mlsanity.com/alignment/reward-hacking-and-misspecification/)

## Builds on (most cited first, 30 of 69)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [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)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Counterfactual Data Augmentation using Locally Factored Dynamics](https://mlsanity.com/paper/2007.02863/) (2020)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [Tree Search for LLM Agent Reinforcement Learning](https://mlsanity.com/paper/2509.21240/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [Hindsight Credit Assignment for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.08754/) (2026)
- [Counterfactual Credit Assignment in Model-Free Reinforcement Learning](https://mlsanity.com/paper/2011.09464/) (2020)
- [Scaling Test-time Compute for LLM Agents](https://mlsanity.com/paper/2506.12928/) (2025)
- [HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale](https://mlsanity.com/paper/2409.16299/) (2024)
- [Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation](https://mlsanity.com/paper/2012.09092/) (2020)
- [Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration](https://mlsanity.com/paper/2406.01422/) (2024)
- [Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study](https://mlsanity.com/paper/2503.15223/) (2025)

## Abstract (arXiv)

Outcome-only reinforcement learning gives software engineering (SWE) agents a terminal success signal but little direct guidance about intermediate decisions. We introduce Counterfactual Rollout Replay (CRR), a training-time procedure that uses forkable executable environments to obtain step-level return contrasts. CRR selects a small set of decision points, restores each state, samples an alternative action, and rolls the branch forward under the policy. It retains the realised training trajectory and replaces the advantage at selected steps with the difference between its terminal return and the sampled counterfactual return. The method needs no human process labels or learned process reward model; free refers to those supervision costs, not replay compute. With a 14B policy, CRR improves pass@1 on SWE-bench Verified, SWE-bench Live, and SWE-rebench, and combines with process-reward and trajectory-search methods. On SWE-bench Verified, an equal-wall-clock comparison on the same hardware yields 41.7% versus 36.7% for extended outcome-only GRPO, a 5.0-point gain with fork overhead included. These results apply to environments with affordable, reliable state restoration; stochastic continuations and expensive or imperfect replay remain limitations.