发表机构
Laboratory for Atomistic and Molecular Mechanics (LAMM); Department of Civil and Environmental Engineering; Department of Biological Engineering; Department of Mechanical Engineering; Center for Computational Science and Engineering; Schwarzman College of Computing; Massachusetts Institute of Technology（原子与分子力学实验室（LAMM）; 土木与环境工程系; 生物工程系; 机械工程系; 计算科学与工程中心; 苏世民计算机学院; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出SwarmWorld框架，让无角色的LLM智能体自组织成技术社会，其协作构建的技术组合比独立搜索更具韧性，揭示了标记介导的技术演化机制。
AI 中文摘要
当个体通过共享环境进行协作时，集体智能会涌现，使局部行动积累成持久的社会组织。语言模型（LLM）智能体为这一过程提供了新的载体，但大多数多智能体系统依赖直接对话、预定义角色或集中式工作流。目前尚不清楚去中心化智能体能否构建功能性技术并优于独立搜索。在SwarmWorld中，初始同质的LLM智能体无需分配角色或配方，自组织成不断演化的技术社会。智能体探索空间环境、加工资源、测试材料、构建持久人工制品，并编写可执行控制器，在智能体移除后，这些控制器会在不可见干扰下由确定性模拟器评估。SwarmWorld将认知与后果分离：智能体在固定的动作和材料模式内提出架构与控制器，而模拟世界决定功能。共享社会发展出比最优N个独立搜索基线更广泛、更具韧性的技术组合，尽管独立搜索在最强人工制品上仍具竞争力。智能体分化为探索、构建、维护和协调行为，随世界成熟而转变。技术通过协作构建、可执行继承和持久的智能体-人工制品网络积累，多数复用始于物理观察而非交流。明确的文化机制会放大协作与组织，但功能收益取决于结果和时间尺度。仅物理标记就能支撑有能力的社会，而互动驱动持久的技术生态，而非普适性更优的个体发明。
英文摘要
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.
