Search

Tag: #multi-agent248 results

GT-HarmBench: Game Theory AI Safety Benchmark

GT-HarmBench: Game Theory AI Safety Benchmark

GT-HarmBench introduces 2,009 high-stakes multi-agent scenarios using game theory like Prisoner's Dilemma to benchmark AI safety risks. Frontier models select socially beneficial actions only 62% of the time, often leading to harm. The benchmark, code, and analysis are available on GitHub.

ArXiv AIResearchFeb 16#research#gt-harmbench#ai-safety
OpenClaw Founder Joins OpenAI

OpenClaw Founder Joins OpenAI

OpenClaw creator Peter Steinberger joins OpenAI for multi-agent AI ideas. Sam Altman eyes agent interactions as core future products. OpenClaw gained fame earlier this year despite security issues.

The VergeMediaFeb 15#research#openai#openclaw
Surveying Multi-Agent Communication Paradigms

Surveying Multi-Agent Communication Paradigms

This survey frames multi-agent communication via the Five Ws, tracing evolution from MARL's hand-designed protocols to emergent language and LLM-based systems. It highlights trade-offs in interpretability, scalability, and generalization across paradigms. Practical design patterns and open challenges are distilled for hybrid systems.

ArXiv AIResearchFeb 13#research#arxiv#multi-agent
PBSAI Multi-Agent AI Governance

PBSAI Multi-Agent AI Governance

PBSAI provides reference architecture for securing enterprise AI estates with multi-agent systems. Organizes 12 domains via agent families, context envelopes, output contracts. Aligns with NIST AI RMF for SOC and hyperscale defense.

ArXiv AIResearchFeb 13#research#pbsai#ai-governance
AgentLeak: Multi-Agent Privacy Leak Benchmark

AgentLeak: Multi-Agent Privacy Leak Benchmark

AgentLeak introduces the first full-stack benchmark for privacy leakage in multi-agent LLM systems, covering internal channels like inter-agent messages. It spans 1,000 scenarios across healthcare, finance, legal, and corporate domains. Tests on top models show internal channels cause 68.9% total leakage, missed by output audits.

ArXiv AIResearchFeb 13#research#agentleak#multi-agent
Page 25 of 25