Research graph
References from Toward effective LLM-based Automated Program Repair: A taxonomy of prompting strategies and key trends, insights, and challenges. Local targets link to admitted publications; unresolved targets remain external evidence.
Utilizing dynamic context and static analysis for agent-based automated program repair
10.1109/access.2026.3691783 · 2026 · External reference
Better patching using llm prompting, via self-consistency
2023 · External reference
Let’s fix this together: Conversational debugging with github copilot
2024 · External reference
10.1109/icse55347.2025.00157
10.1109/icse55347.2025.00157 · External reference
Unresolved reference
2013 · External reference
Adapting knowledge prompt tuning for enhanced automated program repair
2025 · External reference
A study on prompt design, advantages and limitations of chatgpt for deep learning program repair
10.1007/s10515-025-00492-x · 2025 · External reference
Unresolved reference
2021 · External reference
10.1145/3639478.3647633
10.1145/3639478.3647633 · External reference
A comparative study of large language models with chain-of-thought prompting for automated program repair
10.11591/ijai.v14.i6.pp4579-4589 · 2025 · External reference
Advancements in automated program repair: a comprehensive review
2025 · External reference
Using large language models for bug localization and fixing
2023 · External reference
Hierarchical knowledge injection for improving LLM-based program repair
2025 · External reference
Automated repair of programs from large language models
2023 · External reference
Codebert: A pre-trained model for programming and natural languages
2020 · External reference
RetypeR: Integrated retrieval-based automatic program repair for python type errors
2024 · External reference
Towards effectively leveraging execution traces for program repair with code LLMs
2025 · External reference
Large language models for software engineering: A systematic literature review
10.1145/3695988 · 2024 · External reference
Can GPT-O1 kill all bugs? An evaluation of GPT-family LLMs on QuixBugs
2025 · External reference
Evolving paradigms in automated program repair: Taxonomy, challenges, and opportunities
10.1145/3696450 · 2024 · External reference
Unresolved reference
2024 · External reference
Impact of code language models on automated program repair
2023 · External reference
10.1145/3611643.3613892
10.1145/3611643.3613892 · External reference
Rgd: Multi-llm based agent debugger via refinement and generation guidance
2024 · External reference
10.1609/aaai.v37i4.25642
10.1609/aaai.v37i4.25642 · External reference
Explainable automated debugging via large language model-driven scientific debugging
10.1007/s10664-024-10594-x · 2025 · External reference
Unresolved reference
2007 · External reference
ContrastRepair: Enhancing conversation-based automated program repair via contrastive test case pairs
10.1145/3719345 · 2025 · External reference
10.18653/v1/2025.emnlp-main.921
10.18653/v1/2025.emnlp-main.921 · External reference
10.18653/v1/2021.emnlp-main.243
10.18653/v1/2021.emnlp-main.243 · External reference
Context-aware prompting for LLM-based program repair
10.1007/s10515-025-00512-w · 2025 · External reference
Research on program automatic repair method combining context optimization strategy and large language models
2024 · External reference
Debugging engine enhanced by prior knowledge: Can we teach LLM how to debug?
10.1145/3797110 · 2026 · External reference
T3: Multi-level tree-based automatic program repair with large language models
2025 · External reference
ReAPR: Automatic program repair via retrieval-augmented large language models: Z. Liu, X. Du, H. Liu
10.1007/s11219-025-09728-1 · 2025 · External reference
Impact of different buggy code information on large language model-based automated program repair
2026 · External reference
Multi-expert prompting improves reliability, safety, and usefulness of large language models
2024 · External reference
Self-refine: Iterative refinement with self-feedback
10.52202/075280-2019 · 2023 · External reference
Ragfix: Enhancing LLM code repair using RAG and stack overflow postshao2024retyper
2024 · External reference
Astor: Exploring the design space of generate-and-validate program repair beyond GenProg
10.1016/j.jss.2019.01.069 · 2019 · External reference
Experepair: Dual-memory enhanced llm-based repository-level program repair
10.1145/3808181 · 2026 · External reference
Retrieval-based prompt selection for code-related few-shot learning
2023 · External reference
Automated program repair for variability bugs in software product line systems
10.1016/j.jss.2024.112152 · 2025 · External reference
Investigating large language models capabilities for automatic code repair in python
10.1007/s10586-024-04490-8 · 2024 · External reference
Training language models to follow instructions with human feedback
10.52202/068431-2011 · 2022 · External reference
Knowledge-enhanced program repair for data science code
2025 · External reference
The PRISMA 2020 statement: an updated guideline for reporting systematic reviews
2021 · External reference
10.1109/icse55347.2025.00162
10.1109/icse55347.2025.00162 · External reference
10.1145/3524459.3527351
10.1145/3524459.3527351 · External reference
Context matters: Investigating its impact on ChatGPT’s bug fixing performance
2024 · External reference
10.1109/icse-seip66354.2025.00038
10.1109/icse-seip66354.2025.00038 · External reference
SpecRover: Code intent extraction via LLMs
2025 · External reference
Systematic literature review of prompt engineering patterns in software engineering
2024 · External reference
Role play with large language models
10.1038/s41586-023-06647-8 · 2023 · External reference
Hafix: History-augmented large language models for bug fixing
10.1007/s10664-026-10833-3 · 2026 · External reference
An analysis of the automatic bug fixing performance of chatgpt
2023 · External reference
Code repair with llms gives an exploration-exploitation tradeoff
10.52202/079017-3746 · 2024 · External reference
Unresolved reference
2024 · External reference
10.18653/v1/2021.emnlp-main.685
10.18653/v1/2021.emnlp-main.685 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Chain-of-thought prompting elicits reasoning in large language models
10.52202/068431-1800 · 2022 · External reference
10.1145/2601248.2601268
10.1145/2601248.2601268 · External reference
An evaluation of the effectiveness of openai’s chatgpt for automated python program bug fixing using quixbugs
2023 · External reference
Demystifying llm-based software engineering agents
10.1145/3715754 · 2025 · External reference
Automated program repair in the era of large pre-trained language models
2023 · External reference
10.1145/3540250.3549101
10.1145/3540250.3549101 · External reference
10.1145/3650212.3680323
10.1145/3650212.3680323 · External reference
10.1109/icse55347.2025.00169
10.1109/icse55347.2025.00169 · External reference
Unresolved reference
2023 · External reference
Unresolved reference
2025 · External reference
10.1145/3650212.3680328
10.1145/3650212.3680328 · External reference
Tree of thoughts: Deliberate problem solving with large language models
10.52202/075280-0517 · 2023 · External reference
Unresolved reference
External reference
AdverIntent-agent: Adversarial reasoning for repair based on inferred program intent
10.1145/3728939 · 2025 · External reference
10.1145/3650212.3680359
10.1145/3650212.3680359 · External reference
Unveiling the power of code pre-trained models in automated program repair: A systematic review
10.1016/j.jss.2026.113015 · 2026 · External reference
A systematic literature review on large language models for automated program repair
2026 · External reference
PATCH: Empowering large language model with programmer-intent guidance and collaborative-behavior simulation for automatic bug fixing
2025 · External reference
10.1145/3650212.3680384
10.1145/3650212.3680384 · External reference
Towards defect-type-aware adaptive program repair: A stage-wise approach with large language models
10.1007/s11219-026-09751-w · 2026 · External reference
10.1145/3691620.3695537
10.1145/3691620.3695537 · External reference
Debug like a human: A large language model debugger via verifying runtime execution step by step
2024 · External reference
The use of large language models for program repair
10.1016/j.csi.2024.103951 · 2025 · External reference
A study on prompt design, advantages and limitations of chatgpt for deep learning program repair
10.1007/s10515-025-00492-x · ExternalCitation · doi-reference
Context-aware prompting for LLM-based program repair
10.1007/s10515-025-00512-w · ExternalCitation · doi-reference
Investigating large language models capabilities for automatic code repair in python
10.1007/s10586-024-04490-8 · ExternalCitation · doi-reference
Explainable automated debugging via large language model-driven scientific debugging
10.1007/s10664-024-10594-x · ExternalCitation · doi-reference
Hafix: History-augmented large language models for bug fixing
10.1007/s10664-026-10833-3 · ExternalCitation · doi-reference
ReAPR: Automatic program repair via retrieval-augmented large language models: Z. Liu, X. Du, H. Liu
10.1007/s11219-025-09728-1 · ExternalCitation · doi-reference
Towards defect-type-aware adaptive program repair: A stage-wise approach with large language models
10.1007/s11219-026-09751-w · ExternalCitation · doi-reference
The use of large language models for program repair
10.1016/j.csi.2024.103951 · ExternalCitation · doi-reference
Astor: Exploring the design space of generate-and-validate program repair beyond GenProg
10.1016/j.jss.2019.01.069 · ExternalCitation · doi-reference
Automated program repair for variability bugs in software product line systems
10.1016/j.jss.2024.112152 · ExternalCitation · doi-reference
Unveiling the power of code pre-trained models in automated program repair: A systematic review
10.1016/j.jss.2026.113015 · ExternalCitation · doi-reference
Role play with large language models
10.1038/s41586-023-06647-8 · ExternalCitation · doi-reference
Utilizing dynamic context and static analysis for agent-based automated program repair
10.1109/access.2026.3691783 · ExternalCitation · doi-reference
10.1109/icse-seip66354.2025.00038
10.1109/icse-seip66354.2025.00038 · ExternalCitation · doi-reference
10.1109/icse55347.2025.00157
10.1109/icse55347.2025.00157 · ExternalCitation · doi-reference
10.1109/icse55347.2025.00162
10.1109/icse55347.2025.00162 · ExternalCitation · doi-reference
10.1109/icse55347.2025.00169
10.1109/icse55347.2025.00169 · ExternalCitation · doi-reference
10.1145/2601248.2601268
10.1145/2601248.2601268 · ExternalCitation · doi-reference
10.1145/3524459.3527351
10.1145/3524459.3527351 · ExternalCitation · doi-reference
10.1145/3540250.3549101
10.1145/3540250.3549101 · ExternalCitation · doi-reference
10.1145/3611643.3613892
10.1145/3611643.3613892 · ExternalCitation · doi-reference
10.1145/3639478.3647633
10.1145/3639478.3647633 · ExternalCitation · doi-reference
10.1145/3650212.3680323
10.1145/3650212.3680323 · ExternalCitation · doi-reference
10.1145/3650212.3680328
10.1145/3650212.3680328 · ExternalCitation · doi-reference
10.1145/3650212.3680359
10.1145/3650212.3680359 · ExternalCitation · doi-reference
10.1145/3650212.3680384
10.1145/3650212.3680384 · ExternalCitation · doi-reference
10.1145/3691620.3695537
10.1145/3691620.3695537 · ExternalCitation · doi-reference
Large language models for software engineering: A systematic literature review
10.1145/3695988 · ExternalCitation · doi-reference
Evolving paradigms in automated program repair: Taxonomy, challenges, and opportunities
10.1145/3696450 · ExternalCitation · doi-reference
Demystifying llm-based software engineering agents
10.1145/3715754 · ExternalCitation · doi-reference
ContrastRepair: Enhancing conversation-based automated program repair via contrastive test case pairs
10.1145/3719345 · ExternalCitation · doi-reference
AdverIntent-agent: Adversarial reasoning for repair based on inferred program intent
10.1145/3728939 · ExternalCitation · doi-reference
Debugging engine enhanced by prior knowledge: Can we teach LLM how to debug?
10.1145/3797110 · ExternalCitation · doi-reference
Experepair: Dual-memory enhanced llm-based repository-level program repair
10.1145/3808181 · ExternalCitation · doi-reference
A comparative study of large language models with chain-of-thought prompting for automated program repair
10.11591/ijai.v14.i6.pp4579-4589 · ExternalCitation · doi-reference
10.1609/aaai.v37i4.25642
10.1609/aaai.v37i4.25642 · ExternalCitation · doi-reference
10.18653/v1/2021.emnlp-main.243
10.18653/v1/2021.emnlp-main.243 · ExternalCitation · doi-reference
10.18653/v1/2021.emnlp-main.685
10.18653/v1/2021.emnlp-main.685 · ExternalCitation · doi-reference
10.18653/v1/2025.emnlp-main.921
10.18653/v1/2025.emnlp-main.921 · ExternalCitation · doi-reference
Chain-of-thought prompting elicits reasoning in large language models
10.52202/068431-1800 · ExternalCitation · doi-reference
Training language models to follow instructions with human feedback
10.52202/068431-2011 · ExternalCitation · doi-reference
Tree of thoughts: Deliberate problem solving with large language models
10.52202/075280-0517 · ExternalCitation · doi-reference
Self-refine: Iterative refinement with self-feedback
10.52202/075280-2019 · ExternalCitation · doi-reference
Code repair with llms gives an exploration-exploitation tradeoff
10.52202/079017-3746 · ExternalCitation · doi-reference
