让大模型跑步规划更安全可靠，通过分离语言理解与约束求解实现确定性。
SafeRun: Enabling Determinism in LLM Planning for Running
- 大模型负责自然语言规划，专用求解器强制执行安全规则。
- 在五种模型上实现100%安全得分，显著优于基线方法。
- 适合需要高安全性的运动规划场景，如智能穿戴设备应用。
大语言模型虽能灵活进行自然语言规划，但在依赖确定性的安全关键领域仍因概率特性而不可靠。这一问题在跑步规划中尤为突出，违反安全规则可能引发安全隐患。本文提出SafeRun框架，采用解耦架构：大模型负责软性语义理解，确定性求解器严格执行硬性约束，兼顾安全性与语言灵活性。为验证效果，构建了包含真实生理与安全约束的跑步规划综合基准。在五个大模型上的实验表明，SafeRun实现100%安全得分（平均基线79.1%，CodeAct为97.6%），同时保持良好指令遵循能力。该基准已公开于Hugging Face。
原文摘要 · Abstract (English)
Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature. This limitation is especially problematic in running planning, where violating safety rules can lead to safety risks. We propose SafeRun, a framework for deterministic LLM-based planning via a decoupled architecture. SafeRun separates soft interpretation by an LLM from hard constraint enforcement by a deterministic solver, ensuring strict safety constraints while preserving natural-language flexibility. To validate SafeRun, we build a comprehensive benchmark for running planning under realistic physiological and safety constraints. Experiments across five LLMs show that SafeRun achieves 100\% safety score (vs.\ 79.1\% PE average and 97.6\% CodeAct average) while maintaining competitive instruction-following scores. The SafeRun benchmark is publicly available at \href{https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark}{huggingface}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。