# Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction arXiv: https://arxiv.org/abs/2603.02909 ยท HTML: https://mlsanity.com/paper/2603.02909/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 23 of its 36 references that are in the map. - First posted on arXiv 3 Mar 2026. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 23 of 23) - [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024) - [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024) - [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023) - [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020) - [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020) - [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019) - [Zero-Shot Transfer Learning for Event Extraction](https://mlsanity.com/paper/1707.01066/) (2017) - [Unsupervised Label-aware Event Trigger and Argument Classification](https://mlsanity.com/paper/2012.15243/) (2020) - [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022) - [Atomic Fact Decomposition Helps Attributed Question Answering](https://mlsanity.com/paper/2410.16708/) (2024) - [A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction](https://mlsanity.com/paper/2205.00241/) (2022) - [ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement](https://mlsanity.com/paper/2401.13218/) (2024) - [Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction](https://mlsanity.com/paper/2405.01884/) (2024) - [Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?](https://mlsanity.com/paper/2306.00502/) (2023) - [Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance](https://mlsanity.com/paper/2310.05991/) (2023) - [Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction](https://mlsanity.com/paper/2406.12197/) (2024) - [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024) - [Global Constraints with Prompting for Zero-Shot Event Argument Classification](https://mlsanity.com/paper/2302.04459/) (2023) - [LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction](https://mlsanity.com/paper/2311.06555/) (2023) - [Targeted Augmentation for Low-Resource Event Extraction](https://mlsanity.com/paper/2405.08729/) (2024) - [REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction](https://mlsanity.com/paper/2502.16838/) (2025) - [Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization](https://mlsanity.com/paper/2510.13393/) (2025) - [Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore](https://mlsanity.com/paper/2601.15050/) (2026) ## Built on by (most cited first, 2 of 2) - [A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition](https://mlsanity.com/paper/2610.02970/) (2026) - [Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning](https://mlsanity.com/paper/2609.34211/) (2026) ## Abstract (arXiv) Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address the challenge posed by the scarcity of annotated data. However, relying solely on Event-type-only prompts makes it difficult for the generated content to accurately capture the contextual and structural relationships of unseen events. Moreover, ensuring the reliability and usability of synthetic data remains a significant challenge due to the absence of quality evaluation mechanisms. To this end, we introduce a multi-agent collaboration framework for zero-shot document-level event argument extraction (ZS-DEAE), which simulates the human collaborative cognitive process of "Propose-Evaluate-Revise." Specifically, the framework comprises a generation agent and an evaluation agent. The generation agent synthesizes data for unseen events by leveraging knowledge from seen events, while the evaluation agent extracts arguments from the synthetic data and assesses their semantic consistency with the context. The evaluation results are subsequently converted into reward signals, with event structure constraints incorporated into the reward design to enable iterative optimization of both agents via reinforcement learning.In three zero-shot scenarios constructed from the RAMS and WikiEvents datasets, our method achieves improvements both in data generation quality and argument extraction performance, while the generated data also effectively enhances the zero-shot performance of other DEAE models.