Search papers, labs, and topics across Lattice.
This study explores the emergence of collective intelligence among language-model agents in a decentralized environment called SwarmWorld, where agents self-organize to create evolving technological societies without predefined roles. The results indicate that these agents can construct a diverse range of durable artifacts and controllers, outperforming traditional isolated search methods in terms of resilience and technological breadth. Notably, the agents exhibit differentiated roles and behaviors that evolve as the environment matures, demonstrating that physical stigmergy can foster capable societies independently of direct communication.
Language-model agents in SwarmWorld can self-organize to build resilient technological societies, surpassing isolated search methods in innovation and adaptability.
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.
