Metraipolis › archive › dc_35cf694fdf58
DocAtlas: Long-Document Understanding as Mutable-State Interaction — arXiv:2608.07527
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07527
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:49:44.942Z
- SHA-256 of the archived text
a64f509c77f9d750e196cd2b2ee1f4065c4953cc01a52a11d0347e31602ca767- Stable URL of this page
https://metraipolis.com/documento/dc_35cf694fdf58
How to cite
DocAtlas: Long-Document Understanding as Mutable-State Interaction — arXiv:2608.07527 — arXiv (en), https://arxiv.org/abs/2608.07527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35cf694fdf58 (Metraipolis archive dc_35cf694fdf58, sha256 a64f509c77f9d750e196cd2b2ee1f4065c4953cc01a52a11d0347e31602ca767)
BibTeX
@misc{dc35cf694fdf58,
title = {DocAtlas: Long-Document Understanding as Mutable-State Interaction — arXiv:2608.07527},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07527},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35cf694fdf58; sha256 a64f509c77f9d750e196cd2b2ee1f4065c4953cc01a52a11d0347e31602ca767},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-augmented systems usually select evidence from a static index before generation, while recent agentic systems add multi-turn tool use but often rely on frozen proprietary backbones whose behavior is set by prompts. We present DocAtlas, a system that treats long-document understanding as a mutable-state information-seeking process. We instantiate DocAtlas as a mutable document harness: an external environment that determines what document information is searched, read, stored, reviewed, and shown to the model at each step. Given a document and question, the harness exposes search, reading, note-taking, and review tools, maintains a hierarchical tree and note store, and updates both as the agent records evidence. DocAtlas combines self-improving retrieval, selective evidence access, and active working memory under a fixed context budget. The same harness supports inference-time use with large VLMs and end-to-end reinforcement learning for compact VLM agents. With GPT-5.4, DocAtlas reaches 71.4\% on MMLongBench-Doc, exceeding the human-expert reference of 65.8\%. A Qwen3.5-4B VLM trained with end-to-end RL in the DocAtlas environment reaches 63.7\%, compared with a 54.4\% direct-input baseline, showing that mutable document-harness design can improve compact document agents by a large margin. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.07527 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:49:41.819Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).