כתבה
arXiv cs.AI ·
ULTRADISCOVERY: חקירה אבדוקטיבית בעולם קשיש
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe
חקירה אבדוקטיבית בעולם קשיש, המשלבת רעיונות חדשים וכלים כמו LangGraph ו-GPT-5.
תקציר מקורי באנגליתarXiv:2610.03092v1 Announce Type: cross Abstract: 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
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית