Lune

FSE2026Top-tier venue

Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis

Jiahong Xiang, Xiaoyang Xu, Xiaopan Chu, Hongliang Tian, Yuqun Zhang

Abstract

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 out 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ReFLAIR: Detecting Responsive Layout Reflow Issues using Multimodal Generative AIYirui He, Ziyao He, Syed Fatiul Huq, Sam MalekFSE 2026

Builds on21

  1. SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
  2. SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
  3. Teaching Large Language Models to Self-DebugXinyun Chen, Maxwell Lin, Nathanael Schärli, Denny ZhouICLR 2024 · 1,085 citations
  4. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  5. Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 408 citations

Related papers

  1. SWE-PDB: Teaching LLMs to Leverage Debugging Tools via Agentic TrainingJiaxing Liu, Xing Hu, Xin XiaISSTA 2026
  2. Demystifying LLM-Based Software Engineering AgentsChunqiu Steven Xia, Yinlin Deng, Soren Dunn, Lingming ZhangFSE 2025 · 36 citations
  3. InspectCoder: Dynamic Analysis-Driven Self Repair through Interactive LLM-Debugger CollaborationYunkun Wang, Yue Zhang, Guochang Li, Chen Zhi et al.OOPSLA 2026 · 1 citation
  4. SpecRover: Code Intent Extraction via LLMsHaifeng Ruan, Yuntong Zhang, Abhik RoychoudhuryICSE 2025 · 12 citations
  5. To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program RepairZhihao Lin, Junhua Zhu, Mingyi Zhou, Xin Wang et al.ISSTA 2026
Dusk over the sea between two cliffs drawn in fine vertical lines