Sign inGet started
Paper · arXiv

Context as an Environment: Programmatic Context Management for Long-Horizon Agents

LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before future needs are known. We present Scroll, a context manager that treats each agent session as an executable Session Environment. The environment is backed by an append-only Event Log and a sandboxed, persistent Python kernel. The kernel maintains a typed namespace across model calls, allowing tool outputs, retrieved history, and derived state to be bound to variables rather than serialized into the prompt at each call. Model...

AuthorsYin Lin, Elaine Ang, Erkang Zhu et al.
Primary categorycs.AI
Published21 August 2026
Last updated at source21 August 2026
cs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/e4801ac1-39fe-4f46-a29a-80779bde4798" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.