Scroll backs agent sessions with an append-only event log and a persistent Python kernel, hitting 94.8% on LongMemEval_S

arXiv 2608.21690 (submitted 2026-08-21)·medium signalXBlueskyLinkedInCopy link

Alibaba's Scroll (arXiv 2608.21690, submitted 2026-08-21) treats each agent session as an executable environment rather than a compressed chat history. Tool outputs and derived state bind to variables in a typed namespace held by a sandboxed persistent Python kernel, model-written code searches and transforms that state, and only explicitly printed projections enter the next model call. Evicted spans stay recoverable through an eviction index of compact landmarks pointing at exact event log addresses. With Qwen3.8-Max it scores 94.8% on LongMemEval_S, 73.1% on BEAM_10M (5.1 points over the best published memory system) and 86.7% on LOCA_256K, 37.4 points over the best published long-horizon agent.