MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Software EngineeringArtificial Intelligence
Summary
The authors created a new benchmark called MM-IssueLoc to test how well computer programs can find problems in code repositories when given both text and images like screenshots or error messages. Unlike previous tests focusing only on text, this benchmark includes 652 cases with different image types and clear labels for where the issues are in code files or functions. They tested current AI and search tools and found that these tools still struggle to accurately locate problems using visual information. Their work shows that good results on text-only tasks don't guarantee success when images are involved. MM-IssueLoc helps future research check if visual clues actually help find code issues better.
Authors
Shaoxiong Zhan, Shi Hu, Boyu Feng, Hai Lin, Andrew Gong, Zhengda Zhou, Jiaying Zhou, Yunyun Hou, Hao Su, Hai-Tao Zheng
Abstract
Real repository issues routinely include visual evidence such as screenshots, error dialogs, rendered UI states, and logs, yet repository-level issue localization is evaluated mostly as a text-only task. Existing multimodal SE benchmarks evaluate end-to-end repair, entangling localization with patch synthesis and obscuring whether visual input helped, hurt, or was ignored. We introduce \textbf{MM-IssueLoc}, a controlled benchmark and evaluation protocol for repository-level localization with visual evidence. MM-IssueLoc contains 652 issue-PR instances across 23 languages, with annotations for 7 image categories and 4 relevance levels. It provides file-level and function-level gold labels, paired text-only and with-image evaluation, and VCE-based diagnostics that convert images into structured textual evidence. We evaluate LLM-based and retrieval-based systems, including MM-IssueLoc-VL-Emb as a controlled multimodal retriever. Results show that existing systems remain far from reliable multimodal repository localization: the strongest agent reaches 38.96 file Acc@5 and 22.45 function Acc@10, while the strongest retriever reaches 33.86 function Acc@10. Cross-benchmark comparisons show that high localization scores on text-dominant SWE benchmarks do not transfer cleanly to multimodal issue localization. MM-IssueLoc turns visual evidence into an explicit evaluation variable, enabling future work to test whether systems improve by using visual evidence for localization, rather than by relying on text-only cues or downstream patch-generation effects.