Skip to content
English

Switch theme

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

In latest · #376 Added on 2026-10-24

One-line takeaway

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.

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。

23HF upvotes
–GitHub stars
0Citations (Semantic Scholar)
34.2Buzz score

Read on arXiv PDF Hugging Face discussion

About this data

Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.

The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.

Data updated: Latest AI papers(UTC+8)