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

Xietao Wang-Lin, Anton Isopoussu, Louis Mahon
9/9/2026
cs.SEcs.CL

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Do AI models help produce verified bug fixes?

90% match2025

RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair

89% match1 repo442023

An Empirical Study on LLM-based Agents for Automated Bug Fixing

89% match2024

Large Language Models of Code Fail at Completing Code with Potential Bugs

88% match1 repo42026

How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair

87% match2026

SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs

87% match1 repo202025

Cite this paper

@article{wanglin2026its,
  title  = {If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs},
  author = {Xietao Wang-Lin and Anton Isopoussu and Louis Mahon},
  year   = {2026},
  eprint = {2609.10123},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.10123v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.10123.svg)](https://codeofpaper.com/paper/2609.10123)

Discussion