Metraipolis › archive › dc_6b975bdb8267

Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework — arXiv:2609.20973

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20973
License (as archived)
CC0-1.0
Archived
2026-10-10T01:47:25.057Z
SHA-256 of the archived text
e225a4e62806f17873bdc55a8a49a80d28381bdc1f9d4bd356b8a1391ce363b9
Stable URL of this page
https://metraipolis.com/documento/dc_6b975bdb8267

How to cite

Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework — arXiv:2609.20973 — arXiv (en), https://arxiv.org/abs/2609.20973 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b975bdb8267 (Metraipolis archive dc_6b975bdb8267, sha256 e225a4e62806f17873bdc55a8a49a80d28381bdc1f9d4bd356b8a1391ce363b9)
BibTeX
@misc{dc6b975bdb8267,
  title = {Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework — arXiv:2609.20973},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20973},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b975bdb8267; sha256 e225a4e62806f17873bdc55a8a49a80d28381bdc1f9d4bd356b8a1391ce363b9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20973. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-step error amplification, prompt brittleness, and failures to revise incorrect commitments are difficult to explain by missing knowledge or expressive capacity alone. This survey interprets CPS as a sequential estimation-and-decision problem over a latent solution state. A controller maintains a belief about an unobserved solution trajectory, updates it as noisy intermediate evidence arrives, and decides whether to commit, verify, branch, roll back, or abstain to minimize expected loss. Reasoning supplies candidate transitions and interpretations, whereas process control shapes and evaluates those proposals and regulates subsequent transitions and observations. Within this framework, we organize existing methods around five components: explicit state representation, transition structuring, validation and constraint enforcement, search and rollback, and uncertainty management. We also interpret evaluation metrics according to the statistical quantities they estimate. The framework further yields a diagnostic hypothesis: interventions should be most effective when they target the error or uncertainty component implicated by an observed failure. We distinguish systematic, stochastic, and irreducible error together with epistemic and aleatoric uncertainty, and call this alignment problem-control fit and its failure control mismatch. For example, additional sampling may reduce sampling variability while leaving a shared systematic error unchanged. This perspective clarifies what current methods estimate and control, what remains uncontrolled, and why reliable validation, targeted recovery, calibrated uncertainty, and matched-budget evaluation are central open problems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.20973 — 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 2026-10-10T01:14:16.684Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).