Metraipolis › archive › dc_489a5e91dc95

FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows — arXiv:2608.10039

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10039
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:14.297Z
SHA-256 of the archived text
9bb4b60dba2db20202e2650dab6b6f18499479b84a176f15b77cd971d5c53003
Stable URL of this page
https://metraipolis.com/documento/dc_489a5e91dc95

How to cite

FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows — arXiv:2608.10039 — arXiv (en), https://arxiv.org/abs/2608.10039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_489a5e91dc95 (Metraipolis archive dc_489a5e91dc95, sha256 9bb4b60dba2db20202e2650dab6b6f18499479b84a176f15b77cd971d5c53003)
BibTeX
@misc{dc489a5e91dc95,
  title = {FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows — arXiv:2608.10039},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_489a5e91dc95; sha256 9bb4b60dba2db20202e2650dab6b6f18499479b84a176f15b77cd971d5c53003},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures. However, constructing high-quality agentic workflows remains largely manual and requires substantial domain expertise. Recent studies have explored automatic agentic workflow generation from historical task-solving records, but they mainly produce LLM-centric workflows, where real tool executions are abstracted and simulated by LLM nodes, limiting the usability and stability of generated workflows. To address these limitations, we propose FlowScout, an execution-guided framework for generating tool-integrated agentic workflows from historical task-solving records. Specifically, FlowScout represents an agentic workflow as a directed graph composed of LLM nodes, tool-calling nodes, and dependency edges. It first mines a common tool coordination skeleton from historical records to construct an initial workflow, and then refines the workflow topology through Monte Carlo tree search guided by execution feedback. We evaluate FlowScout on four representative task domains and compare it with three baselines, i.e., PM4Py, ReAct and AFlow. Experimental results show that agentic workflows generated by FlowScout improve tool invocation correctness by at least 92.69% and execution quality by at least 17.66% over the baselines, while achieving lower performance variation across repeated runs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10039 — 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 2026-10-19T06:11:45.061Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).