# InstAgent：一种用于异构机器人协作的递归自我改进 Agent 操作系统

> 原文链接：https://robotics.hellobike.com/papers/2026-10-16-2610-23098
> 频道：papers | 更新日期：2026-10-16 | 标签：arxiv, cs.RO
> 核心摘要：针对异构机器人协作中的经验复用、上下文记忆与依赖建模难题，InstAgent以行为树和共享多模态时空记忆组织协作，并在真实多机器人任务上验证。

# InstAgent：一种用于异构机器人协作的递归自我改进 Agent 操作系统

::: v-pre
> 原文链接：[InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration](https://arxiv.org/abs/2610.23098)（arXiv 2610.23098 · 发布日期：2026-10-16）

**InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration**

针对异构机器人协作中的经验复用、上下文记忆与依赖建模难题，InstAgent以行为树和共享多模态时空记忆组织协作，并在真实多机器人任务上验证。

## 核心要点

- 异构机器人团队可结合多种能力执行复杂长程任务，但现有系统难以保留纠错经验、维持交接上下文。
- InstAgent用agentic行为树显式建模能力分配、机器人间依赖与交接检查，并通过RSI从反馈中更新协作程序。
- 在20个真实世界多机器人任务和三个高层模型上，任务成功率、首次完成率与执行效率均持续提升。

**验证范围与局限**：验证范围为20个真实世界多机器人任务和三个高层模型。

## 英文摘要 (Abstract)

Heterogeneous robot teams enable complex, long-horizon tasks by combining complementary sensing, mobility, and manipulation capabilities across multiple embodiments. Yet existing systems struggle to retain execution-time corrections as reusable experience, maintain task-relevant context memory across space and time for reliable handoffs, and explicitly represent the inter-robot dependencies required for structured collaboration. In order to address these challenges, we present InstAgent, a recursively self-improving (RSI) Agent Operating System for heterogeneous robot collaboration. InstAgent organizes team behaviors as agentic behavior trees (BTs) that explicitly model capability assignment, inter-robot dependencies and handoff checks. The RSI mechanism updates these collaboration programs from execution feedback and preserves successful revisions for reuse in future tasks, while shared multimodal spatio-temporal memory provides context for planning and handoff validation. Experiments on 20 real-world multi-robot tasks with three high-level models show consistent gains in task success, first-attempt completion, and execution efficiency.

作者：Haoyang Luo, Junhao Qin, Jingyan Cao, Yi Huang, Guangjie Yang, Xiaoyu Chen, Haotao Lu, Tianxiang Gui, Ye Shi, Jingya Wang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.23098：InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration](https://arxiv.org/abs/2610.23098)