# Is Progressive Disclosure All You Need for Long-Context Agents?

arXiv: https://arxiv.org/abs/2607.17598 · HTML: https://mlsanity.com/paper/2607.17598/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens](https://mlsanity.com/paper/2403.12766/) (2024)
- [Long Context vs. RAG for LLMs: An Evaluation and Revisits](https://mlsanity.com/paper/2501.01880/) (2024)
- [Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG](https://mlsanity.com/paper/2604.14572/) (2026)
- [HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA](https://mlsanity.com/paper/2402.01767/) (2024)
- [Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development](https://mlsanity.com/paper/2603.14805/) (2026)
- [Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows](https://mlsanity.com/paper/2607.07504/) (2026)

## Built on by (most cited first, 3 of 3)

- [SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents](https://mlsanity.com/paper/2608.18852/) (2026)
- [A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes](https://mlsanity.com/paper/2608.27086/) (2026)
- [Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval](https://mlsanity.com/paper/2610.08300/) (2026)

## Abstract (arXiv)

Long-document question answering usually forces a choice between loading the whole document into the context window and bolting on a separate retriever. Agentic AI suggests a broader option, giving the agent the document path and letting it decide how and what to read. Agent Skills, a standard for packaging expertise into folders an agent loads on demand, supply a ready mechanism: progressive disclosure, which exposes only what a query needs, from a short description down to the specific passages. Practitioners rapidly adopted this pattern for book-length understanding tasks, but the evidence to support such choices has been anecdotal. We run the first controlled study of the pattern, comparing raw-document navigation and several designs of Agent Skills packs against a classical hybrid retriever across three agent harnesses and three model families on InfiniteBench. On a single book, the gain depends on the harness, running large when the agent navigates the raw document poorly but near zero when a strong agent harness already divides and retrieves on its own. When scaling up to tasks that span many books, raw-document navigation collapses while one-level progressive disclosure degrades more slowly and pulls ahead. A second, deeper routing level never helps and sometimes breaks accuracy outright, so one level is enough. Progressive disclosure buys context, not intelligence: it is redundant while a strong agent can locate the right passages itself, and decisive once the corpus grows too large to navigate by reading.