# SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

arXiv: https://arxiv.org/abs/2610.12569 · HTML: https://mlsanity.com/paper/2610.12569/

## 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 20 of its 40 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [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)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions](https://mlsanity.com/paper/2405.20267/) (2024)
- [On Leakage of Code Generation Evaluation Datasets](https://mlsanity.com/paper/2407.07565/) (2024)
- [BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills](https://mlsanity.com/paper/2510.19898/) (2025)
- [Automated Benchmark Generation for Repository-Level Coding Tasks](https://mlsanity.com/paper/2503.07701/) (2025)
- [SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration](https://mlsanity.com/paper/2603.03823/) (2026)
- [Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons](https://mlsanity.com/paper/2411.01281/) (2024)
- [Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models](https://mlsanity.com/paper/2503.06643/) (2025)
- [SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving](https://mlsanity.com/paper/2505.23932/) (2025)
- [SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle](https://mlsanity.com/paper/2605.13139/) (2026)
- [RACE-Bench: A Reasoning-Augmented Benchmark for Repository-Level Code Agents on Feature Addition](https://mlsanity.com/paper/2603.26337/) (2026)

## Abstract (arXiv)

Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering tests. The resulting pull request is admitted only if (1) it passes the feature tests and the repository's existing tests while failing exactly the bug tests, and (2) a fresh session of the same agent can repair the bug blind, which rules out unsolvable tasks. The Blue agent then reviews the pull request without being told a bug exists. It wins only if its revision passes all three test suites, and then the two agents swap roles. We run a tournament among 11 model-harness participants on 15 repositories in five languages for 1,500 turns. The leaders win in different ways. GPT-5.5 with Codex CLI ranks first as the strongest solver, repairing 98.3% of the defects it reviews. Claude Opus 4.8 with mini-swe-agent ranks second as the strongest task author, with a 27.3% Red win rate. Finally, within one model family, tasks written by the newest version defeat a fixed-reference solver far more often than those of older versions (42.9% vs. 4.0%), giving preliminary evidence that task difficulty scales with task authoring capability.