Metraipolis › archive › dc_18329fcf4e00

Designing Informative Actions: Action Construction for Long-Horizon Research Agents — arXiv:2611.00773

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00773
License (as archived): CC0-1.0
Archived: 2026-11-03T10:52:19.833Z
SHA-256 of the archived text: 1f57632be12310b268a94128202ff4fe7e201a9bd79b5b107e88167c24d63de7
Stable URL of this page: https://metraipolis.com/documento/dc_18329fcf4e00

How to cite

Designing Informative Actions: Action Construction for Long-Horizon Research Agents — arXiv:2611.00773 — arXiv (en), https://arxiv.org/abs/2611.00773 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18329fcf4e00 (Metraipolis archive dc_18329fcf4e00, sha256 1f57632be12310b268a94128202ff4fe7e201a9bd79b5b107e88167c24d63de7)

BibTeX

@misc{dc18329fcf4e00,
  title = {Designing Informative Actions: Action Construction for Long-Horizon Research Agents — arXiv:2611.00773},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00773},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18329fcf4e00; sha256 1f57632be12310b268a94128202ff4fe7e201a9bd79b5b107e88167c24d63de7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00773. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents support automated scientific research by connecting literature analysis and planning with experimentation. Evaluating which action an agent selects does not establish which experiment its instruction specifies, because omitted interventions or replication counts leave consequential choices to the executor. We introduce a reading-set framework for evaluating action construction under a common cost rule. Across 30 synthetic states, complete-design requests increase affordable efficiency by 465.98% and 327.91% relative to the action-name baseline in the two model families, respectively. An author-constructed research-action evaluation dataset provides 60 scenarios for complementary judgment evaluation. On this dataset, the scenario-level information-per-cost measure has a mean within-scenario correlation of 0.733 with judgments from 18 human participants. The framework makes design specification and execution ambiguity measurable, providing a reproducible basis for assessing how research agents translate scientific intent into informative, budget-feasible experiments.

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/2611.00773 — 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 2026-11-03T10:49:38.271Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).