Problem
Research questions and friction points this paper is trying to address.
Decentralized Agents
Technological Evolution
Collective Intelligence
Language-Model Agents
Stigmergy
SwarmWorld: Stigmergic technological evolution in societies of language-model agents
🤖 AI Summary
研究使用SwarmWorld平台，通过让初始同质的语言模型代理自组织成技术社会，探索了去中心化代理能否构建功能性技术并超越独立搜索。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
SwarmWorld
stigmergic technological evolution
language-model agents
self-organization
technological ecologies
🔎 Similar Papers
No similar papers found.
