arXiv 2609.34565 · cs.AI · 2026-09-28
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Minghao Li, Bangyan Li, Zifan Wang, Yulong Li, Hu Xu, Gan Zhang, Jingtong Wu, Wenqiang Xu
ant-international
在最新榜 #376 本站收录于 2026-10-24
一句话要点
蚂蚁国际的 FlowState 把执行状态当作长程智能体的记忆：保留带语义类型的状态节点、它们的关系和原始工具观察的引用，跨请求保存、按需回看，避免保留全部历史成本太高或压缩后丢细节。
Ant International's FlowState treats execution state as memory for long-horizon LLM agents, keeping semantically typed state nodes, their relations and references to raw tool observations that persist across requests and are revisited on demand, avoiding both full-history cost and lossy compression.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
同机构：ant-international
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。