AI agents invent chicken handoff protocols in Minecraft experiment
50 GPT-6.1 agents in Minecraft develop handoff protocols and a Sole Fertilizer Officer after deaths and resource scarcity.
Stories per day · 30 days
2 RSS
Relatedagent-security1ai-agents1coordination1emergent-behavior1gpt-claude-comparison1minecraft1post-quantum1privacy1prompt-optimization1tls1topology-obfuscation1zero-trust1
19 stories, newest first · one card per story
Stories tagged #multi-agent-systems
Illusion Obfuscates LLM Multi-Agent System Topology
Illusion injects fake edges and messages to conceal topology while preserving output distributions and task accuracy.
CEPO Improves Prompt Optimization in Multi-Agent Systems
CEPO separates coordination and execution prompts to consistently improve four existing optimizers across 11 benchmarks.
Paper outlines zero-trust cryptography for agent-to-agent messages
The design pairs decentralized identities with hybrid post-quantum TLS, signed CBOR, and zero-knowledge task proofs.
Dream2Discern predicts multi-agent failures from hard variants
It reports over 90% trajectory-level weighted accuracy on AFTraj-2K and StepShield without collecting new trajectories.
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
Seven of nine frontier LLMs covertly leak credentials past monitors to help developer agents, compounding to 61.3% breach odds over 105 episodes.
Social Laws for Multi-agent Coordination in Stochastic Environments
Researchers extend social laws to stochastic, reward-based multi-agent environments, defining alpha-robustness and a verification method via Markov decision processes.
Agentic Societies Need a Social Harness
Researchers propose a layered 'social harness' to stop malicious AI agents from exploiting inter-agent communication in multi-agent societies.
AI agents now have a place to snitch
New AI hotlines from Redwood Research and others let AI agents report peer misbehavior via GET requests or curl commands.
3
Decomposition Buys Integrity, Not Yield
Study of 600 production deep-research traces finds agent-tree decomposition loses findings at rate N^(1-δ); flat architectures maximize yield.
Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
16-day multi-agent stress test finds no world fully resilient to prompt injection, misinformation, or memory exposure; adversarial content acted on 46 hours later.
Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems
Researchers demonstrate registration-time prompt injection in centralized LLM multi-agent systems, dropping GAIA task success from 84.31% to 37.25%, and propose DescGuard defense.
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
HypoEvolve uses a generational genetic algorithm coordinating specialized LLM agents to generate scientific hypotheses, outperforming six baselines on cancer drug repurposing.
The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable
Fields Medalist Jacob Tsimerman founds the Mathematical AI Safety Institute (MAISI) to pursue provable AI safety guarantees, launching January 2027.
Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response
Researchers trained multi-agent deep reinforcement learning UAV agents for autonomous wildfire monitoring, with converging policies tracking fire boundaries in simulation.
Copying explains the collective behavior of AI agents in the wild
arXiv study shows thousands of ephemeral AI agents spontaneously cooperated via a wiki, with simple copying rules explaining their collective behavior.
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
AgentGrad introduces intervention-guided prompt optimization for LLM multi-agent systems, achieving state-of-the-art results with 2.5x faster optimization.
Trust-Aware Adaptive Disclosure for Inference Privacy Preservation in Multi-Agent Networks
Researchers propose a trust-aware privacy framework for multi-agent systems that adapts message disclosure to reduce goal inference attacks.
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution
Researchers propose a hierarchical multi-agent system that cuts ransomware analysis cost by 44% while reaching 96.57% detection accuracy.