Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing

Abstract

Large language model-(LLM) based automated program repair (APR) techniques have shown promising results in resolving real-world GitHub issue tasks. Existing APR systems are primarily evaluated in unimodal settings (e.g., SWE-bench). However, these autonomous systems struggle to resolve multimodal problem scenarios (e.g., SWE-bench M) due to limitations in interpreting and leveraging visual information. In multimodal scenarios, LLMs need to rely on visual information in the graphical user interface (GUI) to understand bugs and generate fixes. To bridge this gap, we propose GUIRepair, a cross-modal reasoning approach for resolving multimodal issue scenarios by understanding and capturing visual information. Specifically, GUIRepair integrates two key components, Image2Code and Code2Image, to enhance fault comprehension and patch validation. Image2Code extracts relevant project documents based on the issue report, then applies this domain knowledge to generate the reproduced code responsible for the visual symptoms, effectively translating GUI images into executable context for better fault comprehension. Code2Image replays the visual issue scenario using the reproduced code and captures GUI renderings of the patched program to assess whether the fix visually resolves the issue, providing feedback for patch validation. We evaluate GUIRepair on SWE-bench M, and the approach demonstrates significant effectiveness. When utilizing GPT-4o as the base model, GUIRepair solves 157 instances, outperforming the best open-source baseline by 26 instances. Furthermore, when using o4-mini as the base model, GUIRepair can achieve even better results and solve 175 instances, outperforming the top commercial system by 22 instances. This emphasizes the success of our new perspective on incorporating cross-modal reasoning by understanding and capturing visual information to resolve multimodal issues.

References in corpus (16)

• SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair
• Practical Program Repair in the Era of Large Pre-trained Language Models
• CURE: Code-Aware Neural Machine Translation for Automatic Program Repair
• Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning
• Neural Program Repair with Execution-based Backpropagation
• Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT
• Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair
• How Effective Are Neural Networks for Fixing Security Vulnerabilities
• SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics
• ITER: Iterative Neural Repair for Multi-Location Patches
• Revisiting the Plastic Surgery Hypothesis via Large Language Models
• ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs
• RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair
• Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach
• MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning
• DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models