Metraipolis › archive › dc_c98ff8979968
FlowState: Execution State as Memory for Long-Horizon LLM Agents — arXiv:2609.34565
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34565
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:54.886Z
- SHA-256 of the archived text
27fcaf21959ac6fc7cb4f82ba9688e21ec79c290959d4ebf2597f07acd274901- Stable URL of this page
https://metraipolis.com/documento/dc_c98ff8979968
How to cite
FlowState: Execution State as Memory for Long-Horizon LLM Agents — arXiv:2609.34565 — arXiv (en), https://arxiv.org/abs/2609.34565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c98ff8979968 (Metraipolis archive dc_c98ff8979968, sha256 27fcaf21959ac6fc7cb4f82ba9688e21ec79c290959d4ebf2597f07acd274901)
BibTeX
@misc{dcc98ff8979968,
title = {FlowState: Execution State as Memory for Long-Horizon LLM Agents — arXiv:2609.34565},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34565},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c98ff8979968; sha256 27fcaf21959ac6fc7cb4f82ba9688e21ec79c290959d4ebf2597f07acd274901},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while compressing it risks losing details needed later, and the relevance of historical information often becomes apparent as the task progresses. To address these challenges, we propose FlowState, which treats execution state as memory that can be retained and revisited across requests, unifying current decision-making with the reuse of historical information. FlowState preserves semantically typed state nodes, their relations, and references to raw tool observations, separating persistent retention from on-demand access. Within a single execution loop, Incremental State Update (ISU) maintains the current state based on new inputs and feedback, while Progressive State Access (PSA) progressively reveals historical states and supporting evidence as needed during reasoning. Together, these mechanisms enable agents to reassess prior decisions in light of new information and guide subsequent actions. Compared with a full-context baseline using the same DeepSeek-V4-Flash model, FlowState improves the average success rate on MemoryArena and the average pass rate on $\tau^3$-Bench by 4.55 and 13.95 percentage points, respectively, while reducing total token consumption by 43.2% and 40.6%. These results demonstrate the performance and efficiency advantages of FlowState on long-horizon tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34565 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:01.588Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).