# 通过部分委托给多智能体协议实现异构机器人团队的持续性 LLM 编排

> 原文链接：https://robotics.hellobike.com/papers/2026-10-10-2610-15224
> 频道：papers | 更新日期：2026-10-10 | 标签：arxiv, cs.RO
> 核心摘要：针对动态且不终止任务中的异构机器人团队编排，提出状态摘要、部分委托与重提示机制，并在仿真城市场景验证。

# 通过部分委托给多智能体协议实现异构机器人团队的持续性 LLM 编排

::: v-pre
> 原文链接：[Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols](https://arxiv.org/abs/2610.15224)（arXiv 2610.15224 · 发布日期：2026-10-10）

**Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols**

针对动态且不终止任务中的异构机器人团队编排，提出状态摘要、部分委托与重提示机制，并在仿真城市场景验证。

## 核心要点

- 现有 LLM 编排多假设任务会结束且环境不变，难适应灾害响应等持续动态场景。
- 以每次调用从语义地图重建的马尔可夫状态摘要，替代不断增长的交互历史。
- 通过部分委托把部分机器人交给自主多智能体协议，LLM 专注需细参和排序的子任务。
- 仿真搜救中救援98%平民，强基线为89%，令牌用量少六倍；消融验证各机制贡献。

**验证范围与局限**：验证限于带蔓延火灾和移动疏散者的仿真城市搜救任务。

## 英文摘要 (Abstract)

Natural language specifications let non-expert users task robot teams, and large language models (LLMs) have recently proven effective at grounding such semantic specifications into plans for heterogeneous teams. Existing approaches assume missions that terminate and environments that, while unknown, do not change, but both assumptions fail in many emerging applications. For example, a disaster-response mission does not terminate, and its environment changes continuously as hazards spread and evacuees move. We identify three ways an LLM orchestrator breaks in this setting: its prompt grows without bound, its reasoning degrades as agents and targets accumulate, and it stops actively monitoring after covering the search space once. We build on the successful framework of grounded generative intelligence, and address each issue with a classical idea. A Markovian state summary, rebuilt from the semantic map at every invocation, replaces the growing interaction history. Partial delegation lets the orchestrator assign a subset of robots to an autonomous multi-agent protocol and reserve its reasoning for generating subtasks that require detailed parameters and careful ordering. Lastly, observation staleness, surfaced explicitly in the prompt, together with task-and event-triggered re-prompting, keeps the team vigilant. In a simulated urban search-and-rescue mission with spreading fire and moving evacuees, our framework rescues 98% of civilians versus 89% for the strongest baseline while using six times fewer tokens. Additional ablations isolate the contribution of each mechanism.

作者：Maria G. Mendoza, Victoria Marie Tuck, Zachary Ravichandran, Shankar Sastry, George J. Pappas
:::

## 原始参考来源 (Sources)

- [arXiv 2610.15224：Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols](https://arxiv.org/abs/2610.15224)