# LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues

arXiv: https://arxiv.org/abs/2411.13941 · HTML: https://mlsanity.com/paper/2411.13941/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 21 Nov 2024.

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (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)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [At Which Training Stage Does Code Data Help LLMs Reasoning?](https://mlsanity.com/paper/2309.16298/) (2023)
- [MarsCode Agent: AI-native Automated Bug Fixing](https://mlsanity.com/paper/2409.00899/) (2024)
- [NExT: Teaching Large Language Models to Reason about Code Execution](https://mlsanity.com/paper/2404.14662/) (2024)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration](https://mlsanity.com/paper/2406.01422/) (2024)
- [From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging](https://mlsanity.com/paper/2410.01215/) (2024)
- [WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning](https://mlsanity.com/paper/2312.14187/) (2023)
- [AST-T5: Structure-Aware Pretraining for Code Generation and Understanding](https://mlsanity.com/paper/2401.03003/) (2024)
- [CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2408.13001/) (2024)
- [DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation](https://mlsanity.com/paper/2408.13204/) (2024)
- [Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?](https://mlsanity.com/paper/2410.01353/) (2024)
- [LPR: Large Language Models-Aided Program Reduction](https://mlsanity.com/paper/2312.13064/) (2023)
- [Better Debugging: Combining Static Analysis and LLMs for Explainable Crashing Fault Localization](https://mlsanity.com/paper/2408.12070/) (2024)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code](https://mlsanity.com/paper/2308.03109/) (2023)
- [In-Memory Learning: A Declarative Learning Framework for Large Language Models](https://mlsanity.com/paper/2403.02757/) (2024)

## Built on by (most cited first, 10 of 10)

- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [Otter: Generating Tests from Issues to Validate SWE Patches](https://mlsanity.com/paper/2502.05368/) (2025)
- [SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks](https://mlsanity.com/paper/2506.10954/) (2025)
- [Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation](https://mlsanity.com/paper/2602.08146/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [LLM Agents Can See Code Repositories](https://mlsanity.com/paper/2606.14061/) (2026)
- [Repo0: Design-Driven Zero-to-All Code Generation](https://mlsanity.com/paper/2608.19854/) (2026)
- [Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.03392/) (2026)
- [SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution](https://mlsanity.com/paper/2608.18933/) (2026)
- [Schr"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?](https://mlsanity.com/paper/2609.27891/) (2026)

## Abstract (arXiv)

Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed for this task, they primarily address common, widespread errors and struggle to adapt to unique, evolving errors specific to individual code repositories. To fill this gap, we propose EvoCoder, a multi-agent continuous learning framework for issue code reproduction. EvoCoder adopts a reflection mechanism that allows the LLM to continuously learn from previously resolved problems and dynamically refine its strategies to new emerging challenges. To prevent experience bloating, EvoCoder introduces a novel hierarchical experience pool that enables the model to adaptively update common and repo-specific experiences. Our experimental results show a 20% improvement in issue reproduction rates over existing SOTA methods. Furthermore, integrating our reproduction mechanism significantly boosts the overall accuracy of the existing issue-resolving pipeline.