mlsanityData to 14 Oct 2026

T3: Multi-level Tree-based Automatic Program Repair with Large Language Models

arXiv 2506.21211 ↗First posted 26 Jun 2025cs.SE cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models (LLMs) and the Chain-of-Thought (CoT) techniques have significantly enhanced the reasoning capabilities of these models. However, due to the complex logic and multi-step reasoning ability needed, the application of CoT techniques in the APR domain remains insufficient. This study systematically evaluates the performance of several common CoT techniques in APR tasks and proposes an innovative framework T3, which integrates the powerful reasoning capabilities of LLMs with tree search, effectively improving the precision of generating candidate repair solutions. Furthermore, T3 provides valuable guidance for optimizing sample selection and repair strategies in APR tasks, establishing a robust framework for achieving efficient automated debugging.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 28 of its 33 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

28 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Better patching using LLM prompting, via Self-Consistency31 May

Other references · 27

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  6. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  7. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  9. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  10. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
  11. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  12. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 333
15 more
  1. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  2. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 108
  3. 2023Large Language Models as Analogical Reasonerscited by 107
  4. 2022Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learningcited by 76
  5. 2019TBar: Revisiting Template-based Automated Program Repaircited by 65
  6. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 54
  7. 2021Applying CodeBERT for Automated Program Repair of Java Simple Bugscited by 44
  8. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 44
  9. 2023Conversational Automated Program Repaircited by 41
  10. 2024Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoningcited by 41
  11. 2024A Systematic Literature Review on Large Language Models for Automated Program Repaircited by 37
  12. 2023GAMMA: Revisiting Template-based Automated Program Repair via Mask Predictioncited by 23
  13. 2022DEAR: A Novel Deep Learning-based Approach for Automated Program Repaircited by 22
  14. 2024Atomic Fact Decomposition Helps Attributed Question Answeringcited by 21
  15. 2024IME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completioncited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Automated Repair of C Programs Using Large Language Models
  2. 2025BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions
  3. 2025Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency
  4. 2024ThinkRepair: Self-Directed Automated Program Repair
  5. 2026Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency
  6. 2026Reasoning Distillation for Lightweight Automated Program Repair
  7. 2026From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
  8. 2026RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models