# Scalable Supervision for Software Agents via Patch Reasoning

arXiv: https://arxiv.org/abs/2510.22775 · HTML: https://mlsanity.com/paper/2510.22775/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 15 of 15)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench](https://mlsanity.com/paper/2506.09289/) (2025)
- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning](https://mlsanity.com/paper/2502.20127/) (2025)
- [An Empirical Study on LLM-based Agents for Automated Bug Fixing](https://mlsanity.com/paper/2411.10213/) (2024)

## Built on by (most cited first, 5 of 5)

- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [Dockerless: Environment-Free Program Verifier for Coding Agents](https://mlsanity.com/paper/2606.28436/) (2026)
- [Scaling Coding Agents via Atomic Skills](https://mlsanity.com/paper/2604.05013/) (2026)
- [AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection](https://mlsanity.com/paper/2608.06790/) (2026)
- [LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents](https://mlsanity.com/paper/2609.36371/) (2026)

## Abstract (arXiv)

While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. The reason is twofold: (1) high-coverage tests are naturally rare in the wild, and (2) building and running test sandbox is heavy and fragile. To unlock supervision scaling, we propose R4P, a reasoning-based method that provides scaffold-agnostic rewards. R4P uses a group-wise training objective, enabling it to verify multiple patches against each other's modification and gain a dense reward for supervising agents without executing tests or relying on specific agent trajectories. R4P achieves 72.2% Acc. for verifying patches from SWE-bench, competitive with proprietary models. To show the downstream practical utility of R4P, we design and train an execution-free scaffold, Mini-SE, with pure RL via R4P. Mini-SE achieves 26.2% Pass@1, showing a 10.0% improvement over the original Qwen3-32B, and can be further improved to 32.8% with R4P for test-time scaling on patch selection. The stable scaling curves illustrate that though imperfect, R4P can still reliably support downstream tasks at scale.