tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
It is direct evidence that agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → and context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →-management design, not just the backbone model, drives AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → performance — and that the same environment can train small models to near-frontier results on the task.
Transcript
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.
articlePlan, divide, and conquer: How weak models excel at long context tasksTogether AI
articleFilesystem-Based Memory for LLM Agents: Organization, Evolution, and SustainabilitySizhe Zhou, Sheldon Yu, Hui Wei, Junda Wu, Siru Ouyang, Yizhu Jiao, Shijia Pan, Julian McAuley, Yu Zhang, Tong Yu, Jiawei Han