Metraipolis › archive › dc_6facc6a696db

Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling — arXiv:2608.15565

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15565
License (as archived)
CC0-1.0
Archived
2026-10-18T17:26:02.225Z
SHA-256 of the archived text
09a584a7fb7f231fb8c1f40081d628ea3067ebe718433360ef277d6a8cfee0b7
Stable URL of this page
https://metraipolis.com/documento/dc_6facc6a696db

How to cite

Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling — arXiv:2608.15565 — arXiv (en), https://arxiv.org/abs/2608.15565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6facc6a696db (Metraipolis archive dc_6facc6a696db, sha256 09a584a7fb7f231fb8c1f40081d628ea3067ebe718433360ef277d6a8cfee0b7)
BibTeX
@misc{dc6facc6a696db,
  title = {Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling — arXiv:2608.15565},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15565},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6facc6a696db; sha256 09a584a7fb7f231fb8c1f40081d628ea3067ebe718433360ef277d6a8cfee0b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agents that learn from experience improve at optimization modeling by storing solved trajectories and reusing them as skills. A wrong trajectory that enters the library can be retrieved again and again, and on a stream of new problems there is no ground-truth answer to decide with. Existing learners admit trajectories by matching known optima or labels, and label-free substitutes such as execution success or agreement at one instance can admit wrong models. We introduce ADMITOR, a label-free admission gate. It generates models from three model families, runs each on the stated problem and on instances with resampled parameters, keeps the largest group of models whose optimal values agree on every instance across families, and applies a threshold fitted on solver-verified problems to accept, abstain, or escalate, with a finite-sample bound on the false-discovery rate among accepted values. Inside a state-of-the-art skill learner, ADMITOR raises candidate-level admission precision to 0.927, against 0.871 for majority vote over the host's own samples and 0.726 for execution success, and its library, the smallest of the four, reaches the highest macro accuracy over five public benchmarks, 58.4 against 54.8 for majority vote. An ablation on the same records shows that the gain comes from the accepted value being external to the learner and unanimous across families; on this stream, resampling never changed an accepted value and only reduced coverage. The false-discovery bound holds on the calibration set but not on the benchmark stream: an audit of every false certificate traces most of them to benchmark texts that omit or round the numbers needed to reproduce the labeled answer, and a label-free check of the extracted numbers against the text flags most of these cases.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15565 — 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 2026-10-18T16:29:13.810Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).