Activity Frames：确定性屏幕活动编译用于代理记忆与重放

AI 摘要

Hugging Face 每日论文发布了一篇关于 Activity Frames 的研究，提出了一种确定性、零模型的编译器，可将本地捕获的屏幕活动编译为代理可信任的记忆，并将重复任务转化为可重放脚本。在单用户语料库上，该编译器将一天的原始捕获压缩为 86 倍小的上下文块，耗时 68 毫秒，代理回答问题的准确率达 98.4%，优于 LLM 摘要的 66-80%。研究还首次测量了代理成本参数 R（60-343 倍）和可委托重复率（约 8%），并开源了相关代码。

正文节选

Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay Abstract Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the user said, not what the user did. We compile passively captured screen activity into agent memory with a deterministic, zero-model pipeline: it segments a local capture stream into typed activity frames, bounded episodes carrying application, site, ti

发布时间：—

抓取时间：2026-08-08 02:14

来源机构：Hugging Face