Metraipolis › archive › dc_fc032fa2bd79

Unsatz: Evaluating Scientific Discovery Without a Given Ansatz — arXiv:2611.03713

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03713
License (as archived): CC0-1.0
Archived: 2026-11-04T21:36:25.534Z
SHA-256 of the archived text: 33bd6c79ee1c791be3acf4a097f4b37a8ae183ff86d91e25bb2ae1b18a09babc
Stable URL of this page: https://metraipolis.com/documento/dc_fc032fa2bd79

How to cite

Unsatz: Evaluating Scientific Discovery Without a Given Ansatz — arXiv:2611.03713 — arXiv (en), https://arxiv.org/abs/2611.03713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc032fa2bd79 (Metraipolis archive dc_fc032fa2bd79, sha256 33bd6c79ee1c791be3acf4a097f4b37a8ae183ff86d91e25bb2ae1b18a09babc)

BibTeX

@misc{dcfc032fa2bd79,
  title = {Unsatz: Evaluating Scientific Discovery Without a Given Ansatz — arXiv:2611.03713},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03713},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc032fa2bd79; sha256 33bd6c79ee1c791be3acf4a097f4b37a8ae183ff86d91e25bb2ae1b18a09babc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Before a scientist fits any parameter, they must decide what the model contains: which quantities exist, which are hidden, how they interact, and how they are measured. Physicists call such a trial form an ansatz. Benchmarks for automated equation discovery mostly supply it, by fixing the variables, a library of candidate terms, or a law to be modified. We introduce Unsatz, a benchmark in which an LLM agent must construct the ansatz itself. Each task is a simulated system, generated from a private seed as a program in a small modeling language: ordinary, delay, or partial differential equations, discrete maps, static and causal models, or stochastic processes, possibly with hidden states, distorted sensors, and uninformative measurement channels. The agent buys experiments within a budget, writes candidate programs in the same language, obtains their coefficients from the benchmark's fitter, and is scored only on how its final program predicts experiments it never saw: conditions outside the range it could explore, interventions, and longer runs. Across 80 systems in 20 domains, nine language models solve between 21% and 60%. On 44 of these systems, classical equation-discovery methods almost never succeed, although the same data usually suffice once the true equations are given with unknown coefficients; the difficulty lies in finding the structure, not in estimating it. Because mechanisms recur across systems, we also give agents the program they discovered for a related system; it helped only when the new system shared the mechanism and the first investigation had succeeded. Stronger agents make fewer unscientific errors; beyond these, agents find which variables a system has but not how they act, and prefer revisions that lower the training error to revisions that predict better.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03713 — 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 2026-11-04T21:35:49.486Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).