VisualCoder: Guiding Vision Language Models in Code Execution with Fine-grained Chain-of-Thought Reasoning

Cuong Le Chi, Chau Truong Vinh Hoang, Phan Nhật Huy, Dung D. Le, Tien N Nguyen, Nghi D. Q. Bui

Keywords: Multimodal Large Language Models, Control Flow Graphs, Visualized Code Representation, Code Execution Reasoning, Fault Localization, Program Repair

TL;DR: We present VISUALCODER, a method that enhances LLMs' reasoning on code execution by integrating Control Flow Graphs (CFGs) with Chain-of-Thought (CoT) reasoning.

Abstract: Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce VisualCoder, a novel approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with visual Control Flow Graphs (CFGs). By aligning code snippets with their corresponding CFGs, VisualCoder provides deeper insights into execution flow, enabling more accurate predictions of code behavior. Our experiments demonstrate that augmenting LLMs with visual CFGs significantly outperforms text-based CFG descriptions in code reasoning tasks. We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation.

Primary Area: foundation or frontier models, including LLMs

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.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 13996