Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control· Mimir：长时灌溉控制的物理模型LLM代理
Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and reset failures. Long-running physical control operates in a different regime: actions alter future states, errors compound across decisions, and an agent must improve from experience without being allowed to rewrite the physical rules that make execution safe. We study this regime through irrigation, where daily decisions interact with soil-water dynamics over entire growing seasons. We present Mimir, a physics-grounded LLM agent organized around two repair timescales. At the fast timescale, a structured physical interface and deterministic simulator turn an LLM output into a proposal that we numerically check, revise, an
Mimir 代理结合物理模型与大语言模型，用于长时灌溉控制。
- 核心方法
- Mimir 设计了两个修复时间尺度，快速时间尺度通过结构化的物理接口和确定性模拟器对 LLM 输出进行数值检查和修订；慢速时间尺度则通过经验学习改进策略。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有大语言模型代理主要适用于短期任务，而长时物理控制任务中错误会累积，需要持续改进而不重置。
- 关键实验
- 通过模拟不同生长季节的灌溉任务，验证了 Mimir 代理在长时控制任务中的有效性和改进能力。
- 主要贡献
- 提出了一种适用于长时灌溉控制任务的物理模型与大语言模型相结合的新方法。
- 意义与局限
- 该研究为大语言模型在物理控制领域的应用提供了新的思路，尤其适用于需要持续改进的长时任务，但模型的适用性和泛化能力仍需进一步验证。