Metraipolis › archive › dc_5bd33e32eae9

RISR: Residual-Informed Scientific Equation Discovery with Large Language Models — arXiv:2610.11387

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11387
License (as archived)
CC0-1.0
Archived
2026-10-09T05:57:43.643Z
SHA-256 of the archived text
05b5a093107702ec99293cd9d3fe2e9946f74d373ceb7ce71802c2fce7e58cd2
Stable URL of this page
https://metraipolis.com/documento/dc_5bd33e32eae9

How to cite

RISR: Residual-Informed Scientific Equation Discovery with Large Language Models — arXiv:2610.11387 — arXiv (en), https://arxiv.org/abs/2610.11387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bd33e32eae9 (Metraipolis archive dc_5bd33e32eae9, sha256 05b5a093107702ec99293cd9d3fe2e9946f74d373ceb7ce71802c2fce7e58cd2)
BibTeX
@misc{dc5bd33e32eae9,
  title = {RISR: Residual-Informed Scientific Equation Discovery with Large Language Models — arXiv:2610.11387},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11387},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bd33e32eae9; sha256 05b5a093107702ec99293cd9d3fe2e9946f74d373ceb7ce71802c2fce7e58cd2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a residual-informed method that uses these error patterns to guide formula discovery and learn which corrections are worth fitting. A residual encoder compresses aligned inputs, targets, current predictions, and residuals into continuous tokens that condition a language model to propose formulas. For subsequent refinement, a dual-view relational encoder uses additive and regularized multiplicative residuals to predict the post-fit utility of candidate corrections. We evaluate RISR on scientific tasks from the LLM-SRBench. RISR achieves 63.57% and 38.50% ID accuracy at the 1% and 0.1% pointwise relative-error tolerances, respectively. The corresponding OOD accuracies are 56.07% and 38.24%. RISR outperforms the reported baselines using the same backbone. The results show that our residual-informed approach can improve numerical equation recovery.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Symbolic Computation (cs.SC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.11387 — 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 2026-10-09T05:47:01.617Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).