Metraipolis › archive › dc_b9529ad2aaab

Can Personal Requirements Become Supervision for Planning? — arXiv:2610.40992

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40992
License (as archived)
CC0-1.0
Archived
2026-11-03T07:10:38.740Z
SHA-256 of the archived text
3985244bcd5f9bb9aa8035fbad6457be41c557d4323db69ae9f4374393c299b7
Stable URL of this page
https://metraipolis.com/documento/dc_b9529ad2aaab

How to cite

Can Personal Requirements Become Supervision for Planning? — arXiv:2610.40992 — arXiv (en), https://arxiv.org/abs/2610.40992 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9529ad2aaab (Metraipolis archive dc_b9529ad2aaab, sha256 3985244bcd5f9bb9aa8035fbad6457be41c557d4323db69ae9f4374393c299b7)
BibTeX
@misc{dcb9529ad2aaab,
  title = {Can Personal Requirements Become Supervision for Planning? — arXiv:2610.40992},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40992},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9529ad2aaab; sha256 3985244bcd5f9bb9aa8035fbad6457be41c557d4323db69ae9f4374393c299b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40992. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving established eating habits. These requirements are public in clinical guidelines and drug labels, yet turning them into a feasible plan for one person remains difficult for language-model agents. In our dietitian-approved weekly planning evaluation built from NHANES, thirteen models, from medically fine-tuned 8B models to GPT-6.1 Sol, pass fewer than 3% of complete plans through direct generation. Explicit rules, higher reasoning effort, or model-directed tools leave GPT-6.1 Sol at no more than 8%. We present Noura, which pairs LLM planning with executable personal specifications instantiated from public clinical guidance and individual health and dietary profiles. During planning, the specification grounds foods, optimizes portions, checks the complete multi-day plan, and guides revision. Our key insight is that a specification that rejects a plan can also determine what to learn from it. Noura turns executed plans and contextually credited revisions into supervision for compact models, recovering targets even from trajectories that never achieve complete success. The same specification supplies supervised targets, preferences, and rewards for post-training. On 4,993 held-out participants, Noura-SFT raises Qwen3-14B's complete-plan pass rate from 24.0% to 72.5% within the same execution loop, cuts rule violations by 97.5% with no observed critical failures, and improves dietary quality. The locally hosted 14B planner incurs fewer rule violations than its GPT-6 Luna teacher. A matched comparison shows that executed targets reduce rule violations by 41% over model-written proposals. Across four Qwen, Phi, and Llama backbones, self-training alone reduces rule violations by 41-61% on a 1,249-person population subset.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.40992 — 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 2026-11-03T07:09:31.728Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).