Metraipolis › archive › dc_ff15695c33af

Can LLMs Uncover Hidden Physical Laws through Free Exploration? — arXiv:2610.37649

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37649
License (as archived)
CC0-1.0
Archived
2026-10-28T03:02:08.331Z
SHA-256 of the archived text
3798d818242dc09624e843328c43f689c28ca55071f857c53880886a4b6bb076
Stable URL of this page
https://metraipolis.com/documento/dc_ff15695c33af

How to cite

Can LLMs Uncover Hidden Physical Laws through Free Exploration? — arXiv:2610.37649 — arXiv (en), https://arxiv.org/abs/2610.37649 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff15695c33af (Metraipolis archive dc_ff15695c33af, sha256 3798d818242dc09624e843328c43f689c28ca55071f857c53880886a4b6bb076)
BibTeX
@misc{dcff15695c33af,
  title = {Can LLMs Uncover Hidden Physical Laws through Free Exploration? — arXiv:2610.37649},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37649},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff15695c33af; sha256 3798d818242dc09624e843328c43f689c28ca55071f857c53880886a4b6bb076},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37649. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without being told what to investigate? To evaluate this ability, we introduce LongChang, an automated framework that creates simulated worlds with altered physics, where one or more laws differ from ordinary physics. The evaluated LLMs act as explorers, manipulating objects and building tools to investigate their own questions without research tasks or hints about these laws. Separate LLM agents generate and review scenes, review tool designs, and evaluate reports for correctness and experimental support using the altered physical laws and exploration records. These records guide scene evolution for further exploration, allowing the full cycle to run without human intervention. Among 12 LLMs, GPT-6-Astra achieves a discovery rate of 16.7%, while the other 11 score 0%. The exploration records reveal uninvestigated anomalies and only partial identification of the altered physical laws.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.37649 — 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 2026-10-28T03:01:03.541Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).