# If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs

arXiv: https://arxiv.org/abs/2609.10123 · HTML: https://mlsanity.com/paper/2609.10123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 30 of 34)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025)
- [MarsCode Agent: AI-native Automated Bug Fixing](https://mlsanity.com/paper/2409.00899/) (2024)
- [CodeContests+: High-Quality Test Case Generation for Competitive Programming](https://mlsanity.com/paper/2506.05817/) (2025)
- [A Mechanistic Analysis of Looped Reasoning Language Models](https://mlsanity.com/paper/2604.11791/) (2026)
- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers](https://mlsanity.com/paper/2606.18206/) (2026)
- [When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings](https://mlsanity.com/paper/2407.04503/) (2024)
- [Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing](https://mlsanity.com/paper/2502.15208/) (2025)
- [LLM as a Broken Telephone: Iterative Generation Distorts Information](https://mlsanity.com/paper/2502.20258/) (2025)
- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [The Value Axis: Language Models Encode Whether They're on the Right Track](https://mlsanity.com/paper/2606.17056/) (2026)
- [Attractor States Emerge in Multi-Turn LLM Conversations](https://mlsanity.com/paper/2606.30571/) (2026)
- [ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities](https://mlsanity.com/paper/2506.12376/) (2025)
- [Sparse Reward Subsystem in Large Language Models](https://mlsanity.com/paper/2602.00986/) (2026)
- [Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution](https://mlsanity.com/paper/2606.05408/) (2026)
- [From Restructuring to Stabilization: A Large-Scale Experiment on Iterative Code Readability Refactoring with Large Language Models](https://mlsanity.com/paper/2602.21833/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs as bug-fixers. Across multiple models and repair environments, we find that LLMs consistently claim to detect bugs in entirely bug-free programs while the rate of repair of buggy programs is less than that of the damage to correct programs. We also explore the long-term dynamics of this iterative process, and find that this frequently reaches a pseudo-bug-fixing cycle where the same changes are added and removed again ad infinitum. Lastly, via mechanistic probing, we unveil the existence of a steering vector which controls the editing propensity, suggesting that LLMs have an internal representation of ``buggy code", and that this representation is what is falsely activated to induce pseudo-bug fixing. These results provide insight towards the dynamics of fully autonomous bug-fixing systems, as well as stopping conditions under ambiguous goals.