paper-with-me

홈 › Papers

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

2024-11-21 · Yalan Lin, Yingwei Ma, Rongyu Cao, Binhua Li, Fei Huang, Xiaodong Gu, Yongbin Li

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.

📄 PDF Abstract BibTeX arXiv:2411.13941

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

When Less is More: On the Value of "Co-training" for Semi-Supervised Software Defect Predictors

2022-11-10 · Suvodeep Majumder, Joymallya Chakraborty, Tim Menzies

Labeling a module defective or non-defective is an expensive task. Hence, there are often limits on how much-labeled data is available for training. Semi-supervised classifiers use far fewer labels for training models. H…

Open-Ended Question Answering

BugCraft: End-to-End Crash Bug Reproduction Using LLM Agents in Minecraft

2025-03-25 · Eray Yapağcı, Yavuz Alp Sencer Öztürk, Eray Tüzün

Reproducing game bugs, in our case crash bugs in continuously evolving games like Minecraft, is a notoriously manual, time-consuming, and challenging process to automate. Despite the success of LLM-driven bug reproductio…

Minecraft

Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systems

2026-04-07 · Ike Obi, Vishnunandan L. N. Venkatesh, Weizheng Wang, Ruiqi Wang 외 arxiv

Large Language Models (LLMs) are increasingly used to convert task commands into robot-executable code, however this pipeline lacks validation gates to detect unsafe and defective commands before they are translated into…

Reproduction and Replication: A Case Study with Automatic Essay Scoring

2020-05-01 · LREC 2020 5 · Eva Huber, {\c{C}}a{\u{g}}r{\i} {\c{C}}{\"o}ltekin

As in many experimental sciences, reproducibility of experiments has gained ever more attention in the NLP community. This paper presents our reproduction efforts of an earlier study of automatic essay scoring (AES) for …

Predicting Line-Level Defects by Capturing Code Contexts with Hierarchical Transformers

2023-12-19 · Parvez Mahbub, Mohammad Masudur Rahman

Software defects consume 40% of the total budget in software development and cost the global economy billions of dollars every year. Unfortunately, despite the use of many software quality assurance (SQA) practices in so…

Prediction