---
title: "SwarmWorld：语言模型代理社会中的痕迹驱动技术演化"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.26081v1"
permalink: "https://feed.astralor.com/items/itm_9a52caaec492f39d413c5985"
published: "2026-08-26T17:45:34.000Z"
score: 71
channel: "ai"
tags: ["Stigmergy","SwarmWorld","多智能体系统","语言模型代理","集体智能"]
---

# SwarmWorld：语言模型代理社会中的痕迹驱动技术演化

## AI 点评

> 这篇论文值得关注，因为它把‘留痕’这个自然界的集体智慧机制带到了大模型代理世界，并给出了可复现的实验证据。对研究多智能体协作和人工通用智能的人来说，它指出了去中心化系统里‘环境即媒介’的潜力，不必总是依赖对话或中心调度。对工程者而言，SwarmWorld 的模拟方式也可能成为测试代理技术演化的新工具。

## 速览

SwarmWorld 将语言模型代理置于可交互的模拟环境中，使同质代理无需预设角色或流程即可自组织为技术社会。代理通过探索、资源处理、材料测试和构建持久工件，编写由外部模拟器在代理移除后评估的可执行控制器。实验显示，共享社会能形成比最佳独立搜索更广泛、更具韧性的技术组合，代理还分化出探索、建设、维护和协调等行为，技术积累多始于物理观察而非通信。研究表明，环境痕迹机制足以支撑高效社会协作。

## 关键点

- SwarmWorld 中同质 LLM 代理无需预设分工即可自组织，并通过环境痕迹间接协作。
- 共享社会产出的技术组合比最佳独立搜索基线更广泛、更具韧性，但最强工件上独立搜索仍有竞争力。
- 代理分化出探索、建造、维护和协调等行为，技术积累主要来自物理观察而非直接通信。

## 全文

Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization. Language-model agents offer a new substrate for this process, yet most multi-agent systems rely on direct conversation, predefined roles, or centralized workflows. It remains unclear whether decentralized agents can build functional technologies and outperform independent search. Here, initially homogeneous LLM agents in SwarmWorld self-organize without assigned roles or recipes into evolving technological societies. Agents explore a spatial environment, process resources, test materials, construct persistent artifacts, and write executable controllers evaluated by a deterministic simulator under unseen disturbances after the agents are removed. SwarmWorld splits cognition from consequence: agents propose architectures and controllers within fixed action and material schemas, while the simulated world determines function. Shared societies develop broader, more resilient technological portfolios than a strong best-of-N isolated-search baseline, although isolated search remains competitive for the strongest artifact. Agents differentiate into exploration, construction, maintenance, and coordination behaviors, transitioning as the world matures. Technologies accumulate through collaborative construction, executable inheritance, and persistent agent-artifact networks, with most reuse beginning through physical observation rather than communication. Explicit cultural mechanisms amplify collaboration and organization, but functional benefits depend on outcome and timescale. Physical stigmergy alone supports capable societies, while interaction drives persistent technological ecologies rather than universally superior individual inventions.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_9a52caaec492f39d413c5985