REDO: Execution-Free Runtime Error Detection for Coding Agents

Shuo Li, Andrey Kan, Laurent Callot, Bhavana Bhasker, Muhammad Shihab Rashid, Timothy B Esler

Keywords: error detection, coding agents, runtime, execution-free, large language models

TL;DR: A novel execution free runtime error detection tool for coding agents

Abstract: As LLM-based agents exhibit exceptional capabilities in addressing complex problems, there is a growing focus on developing coding agents to tackle increasingly sophisticated tasks. Despite their promising performance, these coding agents often produce programs or modifications that contain runtime errors, which can cause code failures and are difficult for static analysis tools to detect. Enhancing the ability of coding agents to statically identify such errors could significantly improve their overall performance. In this work, we introduce Execution-free Runtime Error Detection for COding Agents (REDO), a method that integrates LLMs with static analysis tools to detect runtime errors for coding agents, without code execution. Additionally, we propose a benchmark task, SWE-Bench-Error-Detection (SWEDE), based on SWE-Bench (lite), to evaluate error detection in repository-level problems with complex external dependencies. Finally, through both quantitative and qualitative analyses across various error detection tasks, we demonstrate that REDO outperforms current state-of-the-art methods by achieving a 11.0% higher accuracy and 9.1% higher weighted F1 score; and provide insights into the advantages of incorporating LLMs for error detection.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5119