Alibaba's Scroll Lets Models Code Their Own Context Management for Long-Horizon Agents
rohanpaul_ai · x · 2026-08-27
Long-horizon agents often struggle with context window limits, relying on lossy summarization. Scroll, a new framework from Alibaba, shifts this paradigm: it preserves the full event log and uses a persistent Python Kernel, letting the model write code to retrieve relevant information only when needed at query time.
- Core Mechanism: Transforms context management from "rule-based constraints" to "model programming", binding tool outputs to kernel variables instead of pasting them into the prompt.
- Performance: On the BEAM benchmark (where histories exceed current context windows), Scroll (backed by Qwen2.5-72B-Instruct) scored 73.1, outperforming the best published memory system's score of 68.0.
Related event: Alibaba's Scroll Manages Long-Horizon Agent Context via Code(2 posts)→
More from coding & agent
- Dev bills $20,000 for an app built with $200 of Claude Code — IgorCarron · 2026-10-15
- Dan Shipper: run product and labs in parallel, even with a labs team of one — danshipper · 2026-10-15
- Gemini 4 Argon wrote 5,000+ lines of pure Python to build its own ray-tracing 3D engine — aitrendz_xyz · 2026-10-15
- Minecraft fully ported from Java to Rust, file by file, server and client included — Vjeux · 2026-10-15
- mitsuhiko builds a full Python IDE for iOS in an afternoon with new AI models — mitsuhiko · 2026-10-15
- How to get Gemini 4 Argon to build games that actually look decent — chongdashu · 2026-10-15