Metraipolis › archive › dc_2790cb99cb53
Efficient Test-Time Adaptation through Human-AI Interaction — arXiv:2609.04141
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04141
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:11:34.810Z
- SHA-256 of the archived text
bf6a3650d21cd7af8eeb4ee85936eab209b488acddba4bf35b3682951b351805- Stable URL of this page
https://metraipolis.com/documento/dc_2790cb99cb53
How to cite
Efficient Test-Time Adaptation through Human-AI Interaction — arXiv:2609.04141 — arXiv (en), https://arxiv.org/abs/2609.04141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2790cb99cb53 (Metraipolis archive dc_2790cb99cb53, sha256 bf6a3650d21cd7af8eeb4ee85936eab209b488acddba4bf35b3682951b351805)
BibTeX
@misc{dc2790cb99cb53,
title = {Efficient Test-Time Adaptation through Human-AI Interaction — arXiv:2609.04141},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04141},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2790cb99cb53; sha256 bf6a3650d21cd7af8eeb4ee85936eab209b488acddba4bf35b3682951b351805},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data is a rich, underused signal for closing the gap to individual expertise. In this work, we propose test-time adaptation through human-agent interaction (TAHI), which integrates these signals into agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module. We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks. Our agents improve solo task success by 4.5-20.9% within only tens of tasks. Meanwhile, our evolving rubric module serves as a scalable annotation tool, creating evaluation rubrics that catch 16.0-22.3% more failures than those from LMs or humans alone. While agents are adapted towards individuals, we show these personalized agents also produce improvements in success of up to 8.8% that generalize across users. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.04141 — 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 2026-10-17T00:28:02.913Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).