{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:46:23Z","timestamp":1773801983758,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Understanding multi-page documents poses a significant challenge for multimodal large language models (MLLMs), as it requires fine-grained visual comprehension and multi-hop reasoning across pages. While prior work has explored reinforcement learning (RL) for enhancing advanced reasoning in MLLMs, its application to multi-page document understanding remains underexplored. In this paper, we introduce DocR1, an MLLM trained with a novel RL framework, Evidence Page-Guided GRPO (EviGRPO). EviGRPO incorporates an evidence-aware reward mechanism that promotes a coarse-to-fine reasoning strategy, guiding the model to first retrieve relevant pages before generating answers. To support this, we design a rigorous two-stage annotation pipeline and a curriculum learning strategy that enables effective training with limited supervision. Using this pipeline, we construct two datasets: EviBench, a high-quality training set with 4.8k examples, and ArxivFullQA, a benchmark with 8.6k QA examples over full scientific papers. Extensive experiments across a wide range of benchmarks demonstrate that DocR1 achieves state-of-the-art performance on multi-page tasks while maintaining strong results on single-page benchmarks.<\/jats:p>","DOI":"10.1609\/aaai.v40i13.38097","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:07:11Z","timestamp":1773792431000},"page":"11178-11186","source":"Crossref","is-referenced-by-count":0,"title":["DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding"],"prefix":"10.1609","volume":"40","author":[{"given":"Junyu","family":"Xiong","sequence":"first","affiliation":[]},{"given":"Yonghui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Weichao","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Chenyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38097\/42059","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38097\/42059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:07:11Z","timestamp":1773792431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i13.38097","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}