# Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation

arXiv: https://arxiv.org/abs/2510.08996 · HTML: https://mlsanity.com/paper/2510.08996/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 54 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- 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)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason](https://mlsanity.com/paper/2506.12286/) (2025)
- [Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination](https://mlsanity.com/paper/2503.04149/) (2025)
- [Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation](https://mlsanity.com/paper/2406.13990/) (2024)
- [How Novice Programmers Use and Experience ChatGPT when Solving Programming Exercises in an Introductory Course](https://mlsanity.com/paper/2407.20792/) (2024)
- [Unveiling the Role of ChatGPT in Software Development: Insights from Developer-ChatGPT Interactions on GitHub](https://mlsanity.com/paper/2505.03901/) (2025)

## Built on by (most cited first, 15 of 15)

- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures](https://mlsanity.com/paper/2604.03515/) (2026)
- [SWE-Together: Evaluating Coding Agents in Interactive User Sessions](https://mlsanity.com/paper/2606.29957/) (2026)
- [Automated Benchmark Auditing for AI Agents and Large Language Models](https://mlsanity.com/paper/2605.26079/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?](https://mlsanity.com/paper/2608.23564/) (2026)
- [Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent](https://mlsanity.com/paper/2606.22417/) (2026)
- [SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution](https://mlsanity.com/paper/2608.18933/) (2026)
- [Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?](https://mlsanity.com/paper/2602.18571/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents](https://mlsanity.com/paper/2604.16752/) (2026)
- [RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests](https://mlsanity.com/paper/2608.27831/) (2026)
- [What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal](https://mlsanity.com/paper/2609.01271/) (2026)
- [Schr"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?](https://mlsanity.com/paper/2609.27891/) (2026)

## Abstract (arXiv)

Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to accurately reflect how developers interact with chat-based coding assistants in integrated development environments (IDEs). We posit that this mismatch leads to a systematic overestimation of agent's capabilities in real-world scenarios, especially bug fixing. We introduce a novel benchmarking framework that transforms existing formal benchmarks into realistic user queries through systematic analysis of developer interaction patterns with chat-based agents. Our methodology is flexible and can be easily extended to existing benchmarks. In this paper, we apply our testing framework to SWE-Bench Verified, the TypeScript subset of Multi-SWE-Bench and a private benchmark, SWE-Bench C# and transform formal GitHub issue descriptions into realistic user-style queries based on telemetry analysis of a popular chat-based agent interactions. Our findings reveal that existing benchmarks significantly overestimate agent capabilities for some models by >50% over baseline performance for public benchmarks and ~10-16% for our internal benchmark. This work establishes a new paradigm for evaluating interactive chat-based software engineering agents through benchmark mutation techniques.