Metraipolis › archive › dc_2b6e3d66fa4e
From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction — arXiv:2609.13136
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13136
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:15:08.060Z
- SHA-256 of the archived text
eae04a2d7af0018cb5f1eb8c410026901bf457803d1581c6138c23776efe2653- Stable URL of this page
https://metraipolis.com/documento/dc_2b6e3d66fa4e
How to cite
From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction — arXiv:2609.13136 — arXiv (en), https://arxiv.org/abs/2609.13136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b6e3d66fa4e (Metraipolis archive dc_2b6e3d66fa4e, sha256 eae04a2d7af0018cb5f1eb8c410026901bf457803d1581c6138c23776efe2653)
BibTeX
@misc{dc2b6e3d66fa4e,
title = {From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction — arXiv:2609.13136},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13136},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b6e3d66fa4e; sha256 eae04a2d7af0018cb5f1eb8c410026901bf457803d1581c6138c23776efe2653},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents can automate tasks by turning a single natural-language request into a multi-step process spanning tools, files, and applications. Users are often left to judge that process from fragmented execution information and the final output. To make the completed process easier to understand, validate, and reuse, we investigate post-task workflows: editable, graph-based representations of an agent's completed execution. We first analyzed 10,803 public workflow templates from n8n to characterize real-world automation practice, then developed Trace2Flow, a research probe that translates agent execution traces into interactive post-task workflows. In a study, participants (N = 20) reviewed agent executions with prompt or agent errors. We found that post-task workflows improved their understanding and error detection over a prompt-only condition, and that validation succeeded mainly when users cross-checked across multiple evidence sources. For follow-up tasks, adapting the workflow matched adapting the prior prompt in success, time, and difficulty, and was often preferred. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.13136 — 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 2026-10-16T03:05:23.220Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).