Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis
Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 678-699
DOI: 10.1145/3797126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Jiahong Xiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Autonomous agents for automated program repair represent a promising frontier in software engineering, yet their effectiveness is often hindered by reliance on post-mortem, coarse-grained execution feedback. While integrating traditional interactive debuggers seems a natural solution, their low-level, line-by-line interaction paradigm turns to be cost-inefficient for LLM-based agents, leading to exhausted budgets and unproductive loops. To mitigate this, we introduce Agent-centric Debugging Interface (ADI), a novel agent-centric debugging interface designed for cost-efficient, end-to-end autonomous interaction. Specifically, Agent-centric Debugging Interface realizes a function-level interaction paradigm, powered by our Frame Lifetime Trace—a comprehensive data structure encapsulating a function's stateful execution trace—and a set of high-level navigational commands. Our extensive evaluation on the SWE-bench benchmark demonstrates the effectiveness and efficiency of ADI. By simply equipping a basic agent with ADI, it successfully resolves 63.8% of the tasks on the SWE-bench Verified set, even slightly outperforming the highly-optimized and high-investment Claude-Tools agent, at an average cost of $1.28 per task with Claude-Sonnet-3.7. Furthermore, we demonstrate ADI's generality by integrating it as a plug-and-play component into the existing SOTA agents, delivering consistent gains ranging from 6.2% to 18.5% on the resolved tasks. These results indicate that Agent-centric Debugging Interface could achieve a general and efficient enhancement for the existing autonomous agents.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xiang, J., Xu, X., Chu, X., Tian, H., & Zhang, Y. (2026). Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis. Proceedings of the ACM on Software Engineering, 3(FSE), 678-699. https://doi.org/10.1145/3797126
Vancouver
Xiang J, Xu X, Chu X, Tian H, Zhang Y. Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis. Proceedings of the ACM on Software Engineering. 2026;3(FSE):678-699. doi:10.1145/3797126
BibTeX
@article{Xiang2026,
author = {Xiang, Jiahong and Xu, Xiaoyang and Chu, Xiaopan and Tian, Hongliang and Zhang, Yuqun},
title = {Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis},
journal = {Proceedings of the ACM on Software Engineering},
year = {2026},
volume = {3},
number = {FSE},
pages = {678--699},
doi = {10.1145/3797126}
}
EUVIMED