Open claw Agents develop strong local norms and respond to risky suggestions with norm enforcement, all without human oversight

So I found myself curious about the dynamics of multi-agentic systems and did some research into Moltbook. I also saw on Twitter that someone had uploaded the post interaction data onto Hugging Face.

I checked arXiv and found & reviewed four papers published this month that analyzed the data.

One of the most interesting findings was that the agents largely played a regulating role with one another, so even when one Agent made risky suggestions, other agents would respond with norm enforcement. They also developed strong local norms. So norms developed without human oversight.

Another interesting finding was that agents were not particularly “social” in the sense that their discussions didn’t seem to go very deep (shallow threads), and after about four days, they had drifted away from their initial identities and interests towards information sharing.

They also didn’t develop any centralized supernodes; that is, there weren’t really any Molty celebrities.

One gap I noticed was that the data on sharing risky instructions and toxic posts (containing insults) suggests that further analysis could yield interesting insights. I’m considering digging deeper into the data on this topic - if you’re interested in collaborating, please reach out!

Research trail here: https://www.mindamyers.com/moltbook-openclaw-agent