# Agentic Generation of AST Transformation Rules for Fixing Breaking Updates

arXiv: https://arxiv.org/abs/2606.24446 · HTML: https://mlsanity.com/paper/2606.24446/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)
- [An Analysis of the Automatic Bug Fixing Performance of ChatGPT](https://mlsanity.com/paper/2301.08653/) (2023)
- [Learning to Fix Build Errors with Graph2Diff Neural Networks](https://mlsanity.com/paper/1911.01205/) (2019)
- [Do Developers Update Their Library Dependencies? An Empirical Study on the Impact of Security Advisories on Library Migration](https://mlsanity.com/paper/1709.04621/) (2017)
- [An Empirical Comparison of Dependency Network Evolution in Seven Software Packaging Ecosystems](https://mlsanity.com/paper/1710.04936/) (2017)
- [Learning Syntactic Program Transformations from Examples](https://mlsanity.com/paper/1608.09000/) (2016)
- [On Randomness in Agentic Evals](https://mlsanity.com/paper/2602.07150/) (2026)
- [Unprecedented Code Change Automation: The Fusion of LLMs and Transformation by Example](https://mlsanity.com/paper/2402.07138/) (2024)
- [Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs](https://mlsanity.com/paper/2410.08806/) (2024)
- [BUMP: A Benchmark of Reproducible Breaking Dependency Updates](https://mlsanity.com/paper/2401.09906/) (2024)
- [FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration](https://mlsanity.com/paper/2510.04852/) (2025)
- [Breaking Bad? Semantic Versioning and Impact of Breaking Changes in Maven Central](https://mlsanity.com/paper/2110.07889/) (2021)
- [MELT: Mining Effective Lightweight Transformations from Pull Requests](https://mlsanity.com/paper/2308.14687/) (2023)
- [Breaking-Good: Explaining Breaking Dependency Updates with Build Analysis](https://mlsanity.com/paper/2407.03880/) (2024)
- [Byam: Fixing Breaking Dependency Updates with Large Language Models](https://mlsanity.com/paper/2505.07522/) (2025)
- [GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities](https://mlsanity.com/paper/2507.12367/) (2025)
- [Why and How Java Developers Break APIs](https://mlsanity.com/paper/1801.05198/) (2018)
- [Auto-repair without test cases: How LLMs fix compilation errors in large industrial embedded code](https://mlsanity.com/paper/2510.13575/) (2025)
- [SPELL: Synthesis of Programmatic Edits using LLMs](https://mlsanity.com/paper/2602.01107/) (2026)

## Abstract (arXiv)

Modern software projects depend on third-party libraries that evolve continuously, introducing breaking API changes that prevent client code from compiling after a dependency update. When the same library update breaks multiple projects, existing repair approaches generate project-specific patches that cannot be reused, requiring each affected project to be repaired independently. We present BigBag, an agentic framework that generates fixing transformations: structured, executable programs that encode the repair logic at the API level and transfer to any client broken by the same update. We evaluate BigBag on 157 compilation failure breaking dependency updates from the BUMP benchmark, across eight configurations combining four large language models and two AST transformation engines (Spoon and JavaParser). The best configuration achieves a compilable transformation rate of 94.3% and a fix rate of 78.6%. Generated transformations transfer across projects, achieving a cross-project fix rate of 33.3% overall and 80% or above for breaking updates where all clients invoke the affected API element uniformly. These results show that agentic generation of reusable fixing transformations is a viable approach to scalable repair of breaking updates.