We built recursive meta-intelligence, an AI that creates its own scientific instruments, turns them into persistent worlds that an agent ecology with hundreds of AIs inhabits, and uses those worlds to discover mechanistic principles in one of the hardest classes of physical problems: how complex hierarchical materials (nested structures of matter that give rise to new function through organization) evolve and fail. The AI reasons across enormous spaces of possible physical trajectories, where every rupture changes what can happen next, and compresses those histories into principles (which humans can understand and design with) - complex chains of causal events, highly nonlinear, and intricate. Scientific superintelligence is tangible here - machine-scale exploration opening cognitive channels into complexity that has been extremely difficult for humans to traverse directly. AI builds the spaces in which its next level of reasoning becomes possible; a representation becomes an instrument, the instrument becomes an executable world, and that world becomes the substrate for further intelligence. Intelligence then grows by constructing new spaces to think in. The task we explored started from a seemingly simple prompt to explore a biological material system - the AI then chose the representation, mechanics and experiments, built a fracture laboratory to push materials to their limit, tested hypotheses and generated scientific conclusions. The swarm explored a combinatorial universe in which architecture controls function and every rupture changes the future state of the material. The AI discovered a compact principle that defines how multiscale material architecture can program the evolution of failure. Material placement and geometric order determine how forces redistribute, whether damage cascades or remains distributed, and whether function survives substantial flaws. For this discovery to happen the AI had to reason across long path-dependent histories, simulate alternative futures and compress them into generative invariants (model-based causal reasoning, counterfactual simulation and temporal abstraction applied to an evolving physical world). It is incredible to witness this transition to a new form of intelligence and capability through scaling swarms. A lot of positive will come out of this because it expands the human epistemic horizon as AI can traverse thousands of possible histories and return mechanisms compact enough for us to understand, test and build from. Intelligence compounds through its artifacts! A few lessons we learned: ▶️ Learning and discovery are flows through spaces of possibility. Early work has shown how backpropagation flows through parameters, reinforcement learning through action and consequence, and autonomous swarms through representations, instruments and executable worlds, bringing it all together. Flows create structure; structure redirects future flows in the recursive instrument. ▶️ Nonlinear physics actually defines a larger principle, where high-dimensional dynamics generate stable invariants; invariants become effective variables; those variables become the substrate for a new level of cognition. ▶️ Recursion then becomes level creation - one possibility space compresses into a principle, and that principle opens a larger space above it.

Incredibile. AI swarms spontaneously grow scale-free topologies with a few dominant hubs, the Barabási–Albert physics of preferential attachment! Local interactions + rich-get-richer produce the long-tailed degree distribution and information brokers with no central planner. This self-organization without a central planner is the same class of emergent phenomenon seen in many physical systems like phase transitions, self-organized criticality, and spontaneous symmetry breaking where purely local rules generate global structure, information brokers, and efficient long-range integration.

This is a first! The beginning of some very interesting possibilities - your self-driving robot (Tesla) integrated with your team of agents that work with other parts of your ecosystem

incredible, the future is most certainly here.

Two fascinating studies. As a biologist, I get goosebumps thinking about this, even though I had anticipated something of the sort. Especially stigmergy, the division of labor, and an environment that preserves the traces and results of past activities strongly remind me of certain biological systems found in ecosystems. One agent creates something; another encounters it, modifies it, and thereby opens up new possibilities for those who follow. The environment becomes part of the collective memory. 1 / 2

The day matter learned to hear

Fascinating AI swarm dynamics: a few agents spontaneously emerge as highly connected hubs, while most remain locally connected. The swarm develops a strongly heterogeneous interaction topology with a long-tailed degree distribution - an emergent organizational structure arising from initially decentralized local interactions. There is no central planner assigning roles; the swarm builds its own coordination architecture, with information brokers and increasingly global integration emerging from local behavior.

If you work at the intersection of AI and materials discovery, come join us at the ScienceClaw Hackathon at MIT Media Lab! 🚀 We’ll build connected AI-agent systems that combine models, tools, data, simulations, and experiments to tackle hard scientific problems.🤖

Very cool Science AI agent hackathon at MIT Media lab! “The ambition is an internet of agents through which scientific knowledge, tools, and capabilities can grow, evolve and be utilized across teams and institutions.” 🗓️ When: October 30-November 1, 2026 📍 Where: MIT Media Lab

Our lab is organizing a hackathon at MIT - please check it out and join

📅 🚀 It’s GO time! The #S27MRS Call for Abstracts is officially OPEN! Share your work, get feedback, and connect with the global materials community in Seattle.

Rapidly design your own proteins with this new pipeline

Random Access Memories

I would argue that there is nothing more interesting than this research line today

AI is one of the greatest positive forces we have, and I cannot think of anything more human than to understand the world - and to use that power to improve our lives, civilization and allow us to reach beyond what we even dared to imagine.