Metraipolis › archive › dc_cbc30b0123ff
LUCA: A Synthetic World for Experimental Reasoning — arXiv:2611.03100
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03100
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:33:40.354Z
- SHA-256 of the archived text
cc1f7bd42abac42356626bedeaa69d8eb8a3d32133423c779d813200519947d5- Stable URL of this page
https://metraipolis.com/documento/dc_cbc30b0123ff
How to cite
LUCA: A Synthetic World for Experimental Reasoning — arXiv:2611.03100 — arXiv (en), https://arxiv.org/abs/2611.03100 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbc30b0123ff (Metraipolis archive dc_cbc30b0123ff, sha256 cc1f7bd42abac42356626bedeaa69d8eb8a3d32133423c779d813200519947d5)
BibTeX
@misc{dccbc30b0123ff,
title = {LUCA: A Synthetic World for Experimental Reasoning — arXiv:2611.03100},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03100},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbc30b0123ff; sha256 cc1f7bd42abac42356626bedeaa69d8eb8a3d32133423c779d813200519947d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03100. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An experimental agent can succeed for the wrong reasons. Evaluations, however, often focus on the outcome, not the experiments, evidence, and inferences that produced it. We introduce LUCA, a configurable synthetic world for evaluating this process under fully known ground truth. Agents learn unknown regulatory systems through budgeted experimentation, then predict unseen interventions, diagnose hidden faults, and attempt rescues. This setup allows us to evaluate experiment selection, prediction, diagnosis, and intervention separately. Across seven frontier LLMs and three baselines, these capabilities dissociate sharply. Agents frequently rescue malfunctioning systems while diagnosing the wrong fault; diagnosis varies 7x across models while prediction varies only 1.4x. Models also adopt surprisingly different experimental strategies, and greater exploration does not reliably yield better performance. In one failure mode, agents often perform the experiment needed to distinguish competing causes, but still fail to use the resulting evidence. LUCA turns these hidden failures into measurable behaviours, providing a controlled environment to study where experimental agents succeed and fail. Code: this https URL . 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/2611.03100 — 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 2026-11-03T10:29:48.621Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).