← Back to all news
arXiv AI By Aziz Ben Amor, Drish Mali, Mann Acharya, Vijayasri Iyer, S\'ebastien Brati\`eres

RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents

Read the original on arXiv AI →

RefactorPlatform is an open‑source harness that standardizes the evaluation of repository‑scale refactoring agents by fixing the environment and systematically varying design choices such as model backbone, execution regime, and prompt specificity. Each run operates in an isolated workspace, logs detailed telemetry, and verifies changes with AST‑based checks. Experiments on 100 RefactorBench tasks show that AST‑aware chunking improves performance by 25‑30%, a lean retrieval‑augmented single agent outperforms a sub‑agent configuration, and retrieval’s accuracy gains offset its token overhead, keeping cost per successful refactoring unchanged.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 26

REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring

REFINE is a tool-agnostic, evidence-aware multi-agent approach that generates Java file-level refactoring candidates by combining static analysis, smell-informed planning, LLM-based transformation, and automated re-analysis. In experiments on 450 Java files from 15 open-source systems, REFINE reduced detected code smells by 68–73% across three LLM configurations, achieving higher median reductions with smaller edits compared to a direct-prompt baseline. However, the tool’s outputs still pose risks such as assert/fail-call changes and public-method removal, requiring compilation, testing, dependency analysis, and human review before deployment.

By Muhammad Waseem, Aakash Ahmad, Pekka Abrahamsson
llmsagents
More like this →
arXiv AI
Sep 21

DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement

arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to...

By Siyuan Liu (Fudan University, Meituan Longcat Team), Fan Yu (Fudan University, Meituan Longcat Team), Dongyu Ru (Meituan Longcat Team), Yizhu Liu (Meituan Longcat Team), Yifan Yang (Meituan Longcat Team), Xuezhi Cao (Meituan Longcat Team), Xunliang Cai (Meituan Longcat Team), Yixin Cao (Fudan University)
llmsagents
More like this →
arXiv AI
Sep 4

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Terminal-Universe is a framework that transforms large collections of terminal‑based agent trajectories into reusable, executable environments. By replaying recorded file operations and completing missing files, it reconstructs the original workspace and task, then synthesizes new tasks and multi‑round interactions. The resulting 37.3k task‑sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑based benchmarks.

By Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu
agentsfine-tuning
More like this →