HuggingFaceSwarms/avalon-m1
2.7 MB
📚 Research Literature
Research on agent swarms, collective dynamics, and learning to coordinate.
Note Avalon-M1: Reinforcement Learning from Collective Rewards. Original paper: https://gr.inc/avalonm1.pdf
World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds
Paper • 2610.24061 • Published • 8Note Software World: Simulating GitHub with agents — https://www.theagentorg.app/software-world/
-
Learning Self-Orchestration in Decentralized Agent Swarms
Paper • 2610.22322 • Published • 16 -
SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
Paper • 2610.20431 • Published • 24 -
GitSwarm: Decentralized Compounding Inference
Paper • 2610.04862 • Published • 2 -
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
Paper • 2606.02859 • Published • 10