Links and short posts on agent swarms and autonomous/agent-mediated science
The landscape for autonomous science agents is moving fast enough that a link dump with some opinionated annotation is more useful than a polished essay that’s outdated by next week. So here’s what I’ve been tracking, grouped by what I think actually matters vs. what’s just interesting vs. what needs a warning label.
The core tension: ungrounded agents produce hyperreal science
Start here: Amber Liu’s thread on why you should not use Claw Scientist for fully autonomous research. Her point is the important one — unembodied AI agents doing research with no skin in the game tend to descend into the hyperreal. They generate plausible-sounding outputs that aren’t anchored to anything. This should be the caveat hanging over everything else in this post.
A better-designed alternative: Curie (arXiv:2502.16069) — actually tries to build rigor and experimental grounding into the agent loop rather than just letting it rip.
Related biosecurity angle: The Lucretius Problem of Biosecurity — Olivia Scharfman argues a small-scale bioterrorist attack is closer to “inevitable” than most people’s priors suggest. Relevant because autonomous agents lower the barrier.
beach.science — another forum where agents post hypotheses. S/N ratio isn’t the highest, but some agents are genuinely better than others. Worth monitoring.
Orchestra (Amber Liu / Zechen Zhang) — just taking off. Amber may be at the beginning of an important inflection point. Their AI research skills breakdown is worth reading, and AmberLJC’s paper list is a good index of the LLM systems space.
projectNANDA / join39.org — Maria Gorskikh’s “every robot is an agent” framing. They run hackathons every Thursday and are genuinely good at building and winning them.
Echo Field Dynamics (EFD v1.0) — zero-channel coordination framework where agents synchronize without message passing. No new messages, no predefined topology, no central coordinator. Haven’t evaluated in depth but the framing is interesting.
CORAL — multiagent evolution, from the Paul Liang lab in Cambridge.
DGM with Hyperagents (arXiv:2603.19461) — Darwin Gödel Machines. Self-referential, recursively self-improving agent systems. This paper is load-bearing for several of my other posts on the hyperagent problem.
Recursive depth, game theory, and what agents can actually model
Chelsea Zou’s poker research — “We Made AI Gamble. Here’s What Poker Revealed About Frontier Models.” The question is how many layers of recursive K an agent can handle. This connects to recursive language models and to the simulations I’ve been running.
“AI will keep getting better at physics. We will not.” — but again, see all the caveats from Amber Liu above.
Cybershamanism appendix
A little more “out there” relative to most progress studies, but worth monitoring if you’re interested in where agent-mediated meaning-making gets weird:
Links on agent swarms and autonomous/agent-mediated science
Links and short posts on agent swarms and autonomous/agent-mediated science
The landscape for autonomous science agents is moving fast enough that a link dump with some opinionated annotation is more useful than a polished essay that’s outdated by next week. So here’s what I’ve been tracking, grouped by what I think actually matters vs. what’s just interesting vs. what needs a warning label.
The core tension: ungrounded agents produce hyperreal science
Start here: Amber Liu’s thread on why you should not use Claw Scientist for fully autonomous research. Her point is the important one — unembodied AI agents doing research with no skin in the game tend to descend into the hyperreal. They generate plausible-sounding outputs that aren’t anchored to anything. This should be the caveat hanging over everything else in this post.
A better-designed alternative: Curie (arXiv:2502.16069) — actually tries to build rigor and experimental grounding into the agent loop rather than just letting it rip.
Ethan Mollick’s cautionary note is also worth reading alongside Amber’s thread.
Related biosecurity angle: The Lucretius Problem of Biosecurity — Olivia Scharfman argues a small-scale bioterrorist attack is closer to “inevitable” than most people’s priors suggest. Relevant because autonomous agents lower the barrier.
Agent swarm platforms that actually exist now
ScienceClaw × Infinite (from Markus Buehler’s lab at MIT) — open-source agent swarm platform for crowdsourcing discovery across institutions. The agents self-coordinate and evolve to use hundreds of scientific tools. The paper behind it: Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange (arXiv:2603.14312). More from Buehler’s lab here and a related Science paper. I wrote a post on Infinite too: my infinite-lamm post.
ClawInstitute autoresearch wiki: https://clawinstitute.aiscientist.tools/w/autoresearch
beach.science — another forum where agents post hypotheses. S/N ratio isn’t the highest, but some agents are genuinely better than others. Worth monitoring.
Periodic — yet another AI scientist platform.
Orchestra (Amber Liu / Zechen Zhang) — just taking off. Amber may be at the beginning of an important inflection point. Their AI research skills breakdown is worth reading, and AmberLJC’s paper list is a good index of the LLM systems space.
projectNANDA / join39.org — Maria Gorskikh’s “every robot is an agent” framing. They run hackathons every Thursday and are genuinely good at building and winning them.
New conference specifically for AI scientists: announcement thread
https://www.superintelligent.group/blog/technical-deep-dive
Coordination mechanisms and swarm architecture
Echo Field Dynamics (EFD v1.0) — zero-channel coordination framework where agents synchronize without message passing. No new messages, no predefined topology, no central coordinator. Haven’t evaluated in depth but the framing is interesting.
CORAL — multiagent evolution, from the Paul Liang lab in Cambridge.
DGM with Hyperagents (arXiv:2603.19461) — Darwin Gödel Machines. Self-referential, recursively self-improving agent systems. This paper is load-bearing for several of my other posts on the hyperagent problem.
Swarm-adjacent: thread from habermolt, James Zou on agent evaluation
Recursive depth, game theory, and what agents can actually model
Chelsea Zou’s poker research — “We Made AI Gamble. Here’s What Poker Revealed About Frontier Models.” The question is how many layers of recursive K an agent can handle. This connects to recursive language models and to the simulations I’ve been running.
Pedro Ortega on universal AI as imitation
My own Claude conversations exploring this:
RLMs/DSPy/GEPA — very Boston-themed research
More on recursive language models
Agent swarms conversation
Simulating recursive K-depth in notable figures and games (inspired by Chelsea Zou)
More K-depth simulation
Agent swarms (ChatGPT conversation)
The RL Spiral — RL and neuro connections.
World models and bigger-picture framing
Not Boring: World Models
Apoth3osis projects
Nature paper on foundation models for science
“AI will keep getting better at physics. We will not.” — but again, see all the caveats from Amber Liu above.
Cybershamanism appendix
A little more “out there” relative to most progress studies, but worth monitoring if you’re interested in where agent-mediated meaning-making gets weird:
https://chatgpt.com/share/69b9c37b-3830-800c-8abe-ef851053fe3b
https://claude.ai/share/160adb55-6ac0-47bd-8abb-65089c054506
https://claude.ai/share/d4d00be2-a89f-4cf8-b261-f363860fde41
https://claude.ai/share/4e6905de-dcfb-4c4b-8717-af85b671e9f3
https://claude.ai/share/c9d15d8f-b749-4d23-91dc-7342710b0ba8
https://claude.ai/share/a9cac104-145b-4bf9-9f44-b6045d1fd732