# Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect

arXiv: https://arxiv.org/abs/2511.18854 · HTML: https://mlsanity.com/paper/2511.18854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 6 of 6)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization](https://mlsanity.com/paper/2308.05487/) (2023)
- [The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks](https://mlsanity.com/paper/2304.13861/) (2023)

## Abstract (arXiv)

We present a novel framework that integrates Large Language Models (LLMs) into the Git bisect process for semantic fault localization. Traditional bisect assumes deterministic predicates and binary failure states assumptions often violated in modern software development due to flaky tests, nonmonotonic regressions, and semantic divergence from upstream repositories. Our system augments bisect traversal with structured chain of thought reasoning, enabling commit by commit analysis under noisy conditions. We evaluate multiple open source and proprietary LLMs for their suitability and fine tune DeepSeekCoderV2 using QLoRA on a curated dataset of semantically labeled diffs. We adopt a weak supervision workflow to reduce annotation overhead, incorporating human in the loop corrections and self consistency filtering. Experiments across multiple open source projects show a 6.4 point absolute gain in success rate from 74.2 to 80.6 percent, leading to significantly fewer failed traversals and by experiment up to 2x reduction in average bisect time. We conclude with discussions on temporal reasoning, prompt design, and finetuning strategies tailored for commit level behavior analysis.