Metraipolis › archive › dc_2fc9ef6c8b64
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe — arXiv:2610.03092
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03092
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:50:26.823Z
- SHA-256 of the archived text
a322b27666d62af8839175ce9bb9153e016084af85fc202f0dc853a7adb7a6f7- Stable URL of this page
https://metraipolis.com/documento/dc_2fc9ef6c8b64
How to cite
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe — arXiv:2610.03092 — arXiv, https://arxiv.org/abs/2610.03092 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fc9ef6c8b64 (Metraipolis archive dc_2fc9ef6c8b64, sha256 a322b27666d62af8839175ce9bb9153e016084af85fc202f0dc853a7adb7a6f7)
BibTeX
@misc{dc2fc9ef6c8b64,
title = {ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe — arXiv:2610.03092},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03092},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fc9ef6c8b64; sha256 a322b27666d62af8839175ce9bb9153e016084af85fc202f0dc853a7adb7a6f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03092. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing the representation in which an explanation is stated, when the world is epistemically open, and composing evidence scattered across contexts, when it is structurally interconnected. Existing benchmarks rarely separate these two demands or control them independently. We introduce ULTRADISCOVERY, an interactive world of five domains in which an agent revises an initially successful theory and predicts the outcome of an unseen cross-domain intervention. A $2 \times 2$ design leaves the representation open or discloses it, and leaves the evidence distributed or aligns it, with the latent dynamics fixed. With the representation open, agents across eleven models often retract the axiom they were taught, and none introduces the unobserved entity or rewrites the variables that a replacement requires. Disclosure triples intervention requests and adds about one of the eighteen findings the world affords, and alignment adds less. Two vendor-harness systems carry discovery into more domains, and one of them rewrites the variables in Open episodes. No system makes the exact prediction within 200 paid actions. At larger budgets one exact prediction appears with both aids, while every Open episode remains inexact. The results locate the difficulty in the step from accumulating evidence to composing it into a representation that transfers. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.03092 — 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 2026-10-05T22:45:55.827Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).