Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
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 r...
| Authors | Yuanhao Li, Hongbo Wang, Xuhong Chen et al. |
|---|---|
| Primary category | cs.SE |
| Published | 27 September 2026 |
| Last updated at source | 3 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.