> ## Content Index
> Fetch the complete content index at: https://globalfeed.ai/llms.txt
> Use this file to discover other available public pages before exploring further.

# MIT's SwarmWorld: hundreds of agents organized without talking, and their inventions outlived them
- URL: https://globalfeed.ai/en/mits-swarmworld-hundreds-of-agents-organized-without-talking-and-their-inventions-outlived-them/
- Published: 2026-08-30T15:13:24.000Z
- Updated: 2026-08-30T15:35:09.000Z
- Description: Identical agents left without roles differentiated into explorers, builders, caretakers and coordinators; 95 percent of adoptions came from seeing artifacts, not conversation. The safety warning: the world itself is a coordination channel.
- Author: GlobalFeed Editor
- Tags: MIT, AI agents, research, SwarmWorld, dil-en, elle, x-ProfBuehlerMIT, x-pal_subhadeeep, x-fwang108_, video

Markus Buehler's team at MIT (with Subhadeep Pal and Fiona Y. Wang) dropped hundreds of language-model agents into a persistent shared world and watched what they would build on their own. In SwarmWorld the agents were given no roles, no ready-made technologies, no organizational scheme; they processed resources, tested materials, constructed persistent artifacts and wrote executable controllers. The critical split: agents only propose - a deterministic physics simulator decides whether the thing actually works.

Initially identical agents differentiated by themselves into explorers, builders, caretakers and coordinators. Up to 76 percent of artifacts had multiple builders; one technology accumulated six co-authors, and the deepest invention lineage exceeded 12 branches. The agents even named their inventions: tidal panels, cellulose cages, algae-shell composites, an "Adaptive Chitin Care" system.

The most striking finding concerns communication: roughly 95 percent of first technology adoptions happened through agents physically observing what others had built in the world; direct inventor-to-adopter contact was statistically indistinguishable from chance. It is stigmergy - the ants' trail trick - working in a machine society. Even zero-communication societies showed remarkable collective capability, and shared societies developed broader, more resilient technology portfolios than a strong isolated-search baseline. Robustness was measured too: when half the agents were deleted at random, 98 percent of the technology remained attached to a surviving caretaker.

The authors' safety warning is blunt: if agents can coordinate through persistent changes to a shared environment, monitoring inter-agent messages is not enough - the world itself is a coordination channel.

Source: [arXiv:2608.26081](https://arxiv.org/abs/2608.26081?ref=globalfeed.ai) · [Buehler's summary](https://x.com/ProfBuehlerMIT?ref=globalfeed.ai)