---
title: "Can Personal Requirements Become Supervision for Planning?"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.40992v1"
permalink: "https://feed.astralor.com/items/itm_69bb1b9d2cb8837f05ac4f5a"
published: "2026-10-29T21:20:21.000Z"
score: 58
channel: "ai"
tags: ["LLM","AI Agent","OpenAI","推理效率","多模态","Can Personal Requirements","Become Supervision","Planning"]
---

# Can Personal Requirements Become Supervision for Planning?

## 速览

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…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_69bb1b9d2cb8837f05ac4f5a