Metraipolis › archive › dc_5faad307d8b6
PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers — arXiv:2610.32106
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32106
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:47:42.767Z
- SHA-256 of the archived text
fc75142cfcc3fbded49774d76689f64b4de5c95bda2f29be6c63323c7a8ffaf4- Stable URL of this page
https://metraipolis.com/documento/dc_5faad307d8b6
How to cite
PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers — arXiv:2610.32106 — arXiv (en), https://arxiv.org/abs/2610.32106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5faad307d8b6 (Metraipolis archive dc_5faad307d8b6, sha256 fc75142cfcc3fbded49774d76689f64b4de5c95bda2f29be6c63323c7a8ffaf4)
BibTeX
@misc{dc5faad307d8b6,
title = {PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers — arXiv:2610.32106},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32106},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5faad307d8b6; sha256 fc75142cfcc3fbded49774d76689f64b4de5c95bda2f29be6c63323c7a8ffaf4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench: 200 tasks from five benchmarks across four scientific domains. Simulated researchers provide context and feedback according to persona profiles, while task objectives and grading remain fixed. Agents encounter researcher preferences only through conversation. Across eighteen modelconfigurations, task performance, fact recovery, and self-repetition reveal different strengths. Detailed GPT 6 Astra analyses show distinct agent responses across researcher profiles; interaction traces illustrate targeted clar ification and workflow revision. These behaviors can differ even when final scores match. PersonaScienceBench therefore evaluates how agents collaborate with diverse researchers alongside whether they complete the task. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.32106 — 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 2026-10-26T19:45:33.285Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).