agent-sandbox.html 关键词 agent sandbox 的长期追踪 RSS，汇总历史命中文献。 zh-CN Sun, 28 Jun 2026 05:24:06 +0000 ../papers/arxiv-ac86eed4c2bc.html https://arxiv.org/abs/2605.22781v1#2026-05-22#agent-sandbox Fri, 22 May 2026 13:08:19 +0800 LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs. This paper observes that subsequent checkpoints in AI age…