Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 318-326
DOI: 10.1609/aaai.v40i1.36993 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Mingyang Geng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent advances in multi-agent Large Language Model-based code generation enable collaborative software development through role-specialized agents. However, failure localization of code generation remains challenging due to inter-agent dependencies and solution-path multiplicity. Consequently, existing prompting-based localization methods exhibit vulnerability towards semantically valid but non-canonical strategies. To address this, we propose FLKR (Failure Localization via Knowledge-guided Reasoning), an self-supervised framework that combines behavior encoding, knowledge-strategy alignment, and consistency scoring for solution-path invariant localization. To evaluate, we also introduce COFL (Code Oriented Failure Localization), the first expert-annotated benchmark for fine-grained failure localization. Experiments show FLKR outperforms state-of-the-art prompting-based baselines by up to 14 points in Fault Localization Accuracy and 45 points in Top-1 accuracy, with strong performance in divergent, real-world, and refinement-critical cases. Such results demonstrate that our proposed FLKR generalizes well to real-world software development scenarios and opens up a new direction for failure-aware refinement recommendation by providing precise and interpretable responsibility signals.
Zitieren
APA
Geng, M., Gu, S., Liu, Z., Xu, C., Qu, Z., & Wang, H. (2026). Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 318-326. https://doi.org/10.1609/aaai.v40i1.36993
Vancouver
Geng M, Gu S, Liu Z, Xu C, Qu Z, Wang H. Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):318-326. doi:10.1609/aaai.v40i1.36993
BibTeX
@article{Geng2026,
author = {Geng, Mingyang and Gu, Shanzhi and Liu, Zhipeng and Xu, Chuanfu and Qu, Zhaoyang and Wang, Haotian},
title = {Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {1},
pages = {318--326},
doi = {10.1609/aaai.v40i1.36993}
}
EUVIMED