# ChatDBG: Augmenting Debugging with Large Language Models

arXiv: https://arxiv.org/abs/2403.16354 · HTML: https://mlsanity.com/paper/2403.16354/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 48 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [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)
- [Explainable Automated Debugging via Large Language Model-driven Scientific Debugging](https://mlsanity.com/paper/2304.02195/) (2023)
- [Fault Localization with Code Coverage Representation Learning](https://mlsanity.com/paper/2103.00270/) (2021)
- [Engineering Record And Replay For Deployability: Extended Technical Report](https://mlsanity.com/paper/1705.05937/) (2017)

## Built on by (most cited first, 9 of 9)

- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [debug-gym: A Text-Based Environment for Interactive Debugging](https://mlsanity.com/paper/2503.21557/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer](https://mlsanity.com/paper/2409.11190/) (2024)
- [Adversarial Reasoning for Repair Based on Inferred Program Intent](https://mlsanity.com/paper/2505.13008/) (2025)
- [Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?](https://mlsanity.com/paper/2602.18571/) (2026)
- [Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis](https://mlsanity.com/paper/2604.24212/) (2026)
- [JupOtter: Cell-Level Bug Detection in Jupyter Notebooks](https://mlsanity.com/paper/2606.23877/) (2026)
- [AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies](https://mlsanity.com/paper/2608.02569/) (2026)

## Abstract (arXiv)

Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like "why is x null?". To handle these queries, ChatDBG grants the LLM autonomy to "take the wheel": it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. By leveraging the real-world knowledge embedded in LLMs, ChatDBG can diagnose issues identifiable only through the use of domain-specific reasoning. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded more than 75,000 times.