# ThinkRepair: Self-Directed Automated Program Repair arXiv: https://arxiv.org/abs/2407.20898 ยท HTML: https://mlsanity.com/paper/2407.20898/ ## Key facts - Cited by 23 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 4 of its 49 references that are in the map. - First posted on arXiv 30 Jul 2024. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) ## Builds on (most cited first, 4 of 4) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023) - [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023) ## Built on by (most cited first, 23 of 23) - [From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging](https://mlsanity.com/paper/2410.01215/) (2024) - [Issue Localization via LLM-Driven Iterative Code Graph Searching](https://mlsanity.com/paper/2503.22424/) (2025) - [SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs](https://mlsanity.com/paper/2504.14757/) (2025) - [ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.02330/) (2025) - [TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code](https://mlsanity.com/paper/2602.06875/) (2026) - [Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications](https://mlsanity.com/paper/2508.12358/) (2025) - [AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities](https://mlsanity.com/paper/2505.04195/) (2025) - [Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement](https://mlsanity.com/paper/2603.00539/) (2026) - [AuPair: Golden Example Pairs for Code Repair](https://mlsanity.com/paper/2502.18487/) (2025) - [Evaluating the Generalizability of LLMs in Automated Program Repair](https://mlsanity.com/paper/2503.09217/) (2025) - [Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair](https://mlsanity.com/paper/2606.30963/) (2026) - [VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution](https://mlsanity.com/paper/2601.13933/) (2026) - [Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs](https://mlsanity.com/paper/2604.20211/) (2026) - [Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation](https://mlsanity.com/paper/2509.25243/) (2025) - [FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification](https://mlsanity.com/paper/2604.03245/) (2026) - [Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs](https://mlsanity.com/paper/2607.12605/) (2026) - [Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency](https://mlsanity.com/paper/2608.14065/) (2026) - [From Benchmark Data To Applicable Program Repair: An Experience Report](https://mlsanity.com/paper/2508.16071/) (2025) - [SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study](https://mlsanity.com/paper/2510.10010/) (2025) - [Knowledge-Enhanced Agentic Vulnerability Repair](https://mlsanity.com/paper/2607.00820/) (2026) - [Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests](https://mlsanity.com/paper/2607.22883/) (2026) - [Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills](https://mlsanity.com/paper/2609.12012/) (2026) - [RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair](https://mlsanity.com/paper/2610.04658/) (2026) ## Abstract (arXiv) Though many approaches have been proposed for Automated Program Repair (APR) and indeed achieved remarkable performance, they still have limitations in fixing bugs that require analyzing and reasoning about the logic of the buggy program. Recently, large language models (LLMs) instructed by prompt engineering have attracted much attention for their powerful ability to address many kinds of tasks including bug-fixing. However, the quality of the prompt will highly affect the ability of LLMs and manually constructing high-quality prompts is a costly endeavor. To address this limitation, we propose a self-directed LLM-based automated program repair, ThinkRepair, with two main phases: collection phase and fixing phase. The former phase automatically collects various chains of thoughts that constitute pre-fixed knowledge by instructing LLMs with the Chain-of-Thought (CoT) prompt. The latter phase targets fixing a bug by first selecting examples for few-shot learning and second automatically interacting with LLMs, optionally appending with feedback of testing information. Evaluations on two widely studied datasets (Defects4J and QuixBugs) by comparing ThinkRepair with 12 SOTA APRs indicate the priority of ThinkRepair in fixing bugs. Notably, ThinkRepair fixes 98 bugs and improves baselines by 27%-344.4% on Defects4J V1.2. On Defects4J V2.0, ThinkRepair fixes 12-65 more bugs than the SOTA APRs. Additionally, ThinkRepair also makes a considerable improvement on QuixBugs (31 for Java and 21 for Python at most).