Metraipolis › archive › dc_4884716366fc

Reusable LLM-Based Plans with Probabilistic Guarantees for Self-Adaptive Systems — arXiv:2610.38039

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.38039
License (as archived): CC0-1.0
Archived: 2026-11-01T02:28:57.038Z
SHA-256 of the archived text: 7231423106b148f1d4861f4a4c8c85a686947c1918ad6b4b5443585c51732798
Stable URL of this page: https://metraipolis.com/documento/dc_4884716366fc

How to cite

Reusable LLM-Based Plans with Probabilistic Guarantees for Self-Adaptive Systems — arXiv:2610.38039 — arXiv (en), https://arxiv.org/abs/2610.38039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4884716366fc (Metraipolis archive dc_4884716366fc, sha256 7231423106b148f1d4861f4a4c8c85a686947c1918ad6b4b5443585c51732798)

BibTeX

@misc{dc4884716366fc,
  title = {Reusable LLM-Based Plans with Probabilistic Guarantees for Self-Adaptive Systems — arXiv:2610.38039},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4884716366fc; sha256 7231423106b148f1d4861f4a4c8c85a686947c1918ad6b4b5443585c51732798},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-adaptive systems are designed to accommodate variants of their environment, which form a family of instances whose uncertainty is captured by probabilistic models, and must meet probabilistic requirements on each instance. Within such a family, changes in size and structure complicate the fundamental adaptation decision: whether to retain, reuse, or construct a new controller, since controllers are often synthesized for and specific to an instance. Large language models (LLMs) have recently been used to write reusable controllers, but existing approaches largely target deterministic domains, and probabilistic model checking of their output remains limited to preliminary single-instance studies. In this paper, we propose a verifier-guided framework for controller reuse with explicit support for families of environments. The framework introduces a novel combination of LLM-written controllers with probabilistic model checking to provide per-instance guarantees for probabilistic requirements. We evaluate our approach using three LLMs on three benchmarks, assessing its effectiveness and cost with respect to baseline implementations, the distribution of adaptation decisions, and the impact of individual framework components. On grid worlds, LLM-written rule lists are verified on about 90% of held-out instances, against at most 77% for the baselines, and verifying a stored rule list is 15 to 103 times faster than per-instance synthesis. Reuse serves most episodes at a small fraction of the cost of generation or per-instance synthesis, and model-checking feedback increases verified coverage over independent restarts.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.38039 — 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 2026-11-01T02:12:58.472Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).