SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2609.29230 · September 2026

EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards

Daniel Sonntag, Omar Adjali, Siting Liang, Omair Shahzad Bhatti

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extraction of schema-grounded argument spans. We present EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards. Our reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision. Experiments across seven benchmark datasets show that EAGER consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method. Results demonstrate that task-aligned verifiable rewards and contrastive advantage estimation substantially improve structured extraction.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2609.29230")
get_code_for_paper("2609.29230")
have("2609.29230")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2609.29230.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2609.29230.svg)](https://syntology.ai/paper/2609.29230)

Connect an agent — have() is free.