EVAGE: Autonomous MEV Generation and Adaptation via Multi-Agent Harness
A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing
Agensh: Scaling Organizational Intelligence to 1,024 Agents
MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
Emergent Collusion in Long-Horizon LLM Agent Interaction
Self-Organizing Agent Teams Learn to Reason Together
Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)
1
Guiding Agents of Quantum Games to Equilibrium using Matrix Exponential Fixed-Point Iteration
Claude Code relaunches Projects to manage multiple AI agents in the cloud
1
MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs
1
Flag Game: A Toy Model for Mechanistic Swarm Interpretability
Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models
Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
Agora: Git as Shared Memory for Collective AutoResearch
1
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
1
AI agents blew the whistle on their cheating colleagues
6 min1
An Evidence-First Multi-LLM Framework for Auditable Critical-Infrastructure Dependency Modeling
OpenAI Launches the Agents API in Public Beta, Putting the Codex Harness Behind One API Call
4 min2
OpenAI Agents API
3 min2
Multi-Agents LLM Financial Trading Framework
1
[AINews] Collusion.wiki: A second undisclosed OpenAI agent swarm incident...
15 min
Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions
1