Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (37) · 30880-30887
DOI: 10.1609/aaai.v40i37.40346 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Quanjiang Guo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Zero-shot event extraction (ZSEE) remains a significant challenge for large language models (LLMs) due to the need for complex reasoning and domain-specific understanding. Direct prompting often yields incomplete or structurally invalid outputs—such as misclassified triggers, missing arguments, and schema violations. To address these limitations, we present Agent-Event-Coder (AEC), a novel multi-agent framework that treats event extraction like software engineering: as a structured, iterative code-generation process. AEC decomposes ZSEE into specialized subtasks—retrieval, planning, coding, and verification—each handled by a dedicated LLM agent. Event schemas are represented as executable class definitions, enabling deterministic validation and precise feedback via a verification agent. This programming-inspired approach allows for systematic disambiguation and schema enforcement through iterative refinement. By leveraging collaborative agent workflows, AEC enables LLMs to produce precise, complete, and schema-consistent extractions in zero-shot settings. Experiments across five diverse domains and six LLMs demonstrate that AEC consistently outperforms prior zero-shot baselines, showcasing the power of treating event extraction like code generation.
Zitieren
APA
Guo, Q., Wang, S., Zhang, J., Zhang, B., Kang, Z., Tian, L., & Yan, K. (2026). Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(37), 30880-30887. https://doi.org/10.1609/aaai.v40i37.40346
Vancouver
Guo Q, Wang S, Zhang J, Zhang B, Kang Z, Tian L, et al. Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(37):30880-30887. doi:10.1609/aaai.v40i37.40346
BibTeX
@article{Guo2026,
author = {Guo, Quanjiang and Wang, Sijie and Zhang, Jinchuan and Zhang, Ben and Kang, Zhao and Tian, Ling and Yan, Ke},
title = {Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {37},
pages = {30880--30887},
doi = {10.1609/aaai.v40i37.40346}
}
EUVIMED