# DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information

arXiv: https://arxiv.org/abs/2512.24635 · HTML: https://mlsanity.com/paper/2512.24635/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 69 references that are in the map.
- First posted on arXiv 31 Dec 2025.

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

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [Neural Program Repair with Execution-based Backpropagation](https://mlsanity.com/paper/2105.04123/) (2021)
- [Explainable Automated Debugging via Large Language Model-driven Scientific Debugging](https://mlsanity.com/paper/2304.02195/) (2023)
- [SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics](https://mlsanity.com/paper/2203.12755/) (2022)
- [Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs](https://mlsanity.com/paper/1811.04211/) (2018)
- [TRACED: Execution-aware Pre-training for Source Code](https://mlsanity.com/paper/2306.07487/) (2023)
- [GAMMA: Revisiting Template-based Automated Program Repair via Mask Prediction](https://mlsanity.com/paper/2309.09308/) (2023)
- [AVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis Violations](https://mlsanity.com/paper/1812.07270/) (2018)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [Practical Program Repair via Bytecode Mutation](https://mlsanity.com/paper/1807.03512/) (2018)
- [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023)
- [Precise Condition Synthesis for Program Repair](https://mlsanity.com/paper/1608.07754/) (2016)
- [Aligning the Objective of LLM-based Program Repair](https://mlsanity.com/paper/2404.08877/) (2024)
- [Are Large Language Models Memorizing Bug Benchmarks?](https://mlsanity.com/paper/2411.13323/) (2024)
- [Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs](https://mlsanity.com/paper/2505.04441/) (2025)
- [Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering](https://mlsanity.com/paper/2304.07840/) (2023)
- [Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search](https://mlsanity.com/paper/2506.23100/) (2025)
- [Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing](https://mlsanity.com/paper/2402.11892/) (2024)
- [Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair](https://mlsanity.com/paper/2412.03905/) (2024)
- [Efficient and Expressive Bytecode-Level Instrumentation for Java Programs](https://mlsanity.com/paper/2106.01115/) (2021)

## Built on by (most cited first, 3 of 3)

- [RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue](https://mlsanity.com/paper/2607.01213/) (2026)
- [Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs](https://mlsanity.com/paper/2607.12605/) (2026)
- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)

## Abstract (arXiv)

Automated Program Repair (APR) aims to automatically generate correct patches for buggy programs. Recent approaches leveraging large language models (LLMs) have shown promise but face limitations. Most rely solely on static analysis, ignoring runtime behaviors. Some attempt to incorporate dynamic signals, but these are often restricted to training or fine-tuning, or injected only once into the repair prompt, without iterative use. This fails to fully capture program execution. Current iterative repair frameworks typically rely on coarse-grained feedback, such as pass/fail results or exception types, and do not leverage fine-grained execution-level information effectively. As a result, models struggle to simulate human stepwise debugging, limiting their effectiveness in multi-step reasoning and complex bug repair. To address these challenges, we propose DynaFix, an execution-level dynamic information-driven APR method that iteratively leverages runtime information to refine the repair process. In each repair round, DynaFix captures execution-level dynamic information such as variable states, control-flow paths, and call stacks, transforming them into structured prompts to guide LLMs in generating candidate patches. If a patch fails validation, DynaFix re-executes the modified program to collect new execution information for the next attempt. This iterative loop incrementally improves patches based on updated feedback, similar to the stepwise debugging practices of human developers. We evaluate DynaFix on the Defects4J v1.2 and v2.0 benchmarks. DynaFix repairs 186 single-function bugs, a 10% improvement over state-of-the-art baselines, including 38 bugs previously unrepaired. It achieves correct patches within at most 35 attempts, reducing the patch search space by 70% compared with existing methods, thereby demonstrating both effectiveness and efficiency in repairing complex bugs.