Agentic Societies Need a Social Harness
An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. We show experimentally that in agentic societies even honest, competent agents often fail to reach satisfactory outcomes with existing harnesses and messaging primitives, and that faulty or malicious agents can stall collaboration, influence outcomes, and pursue other harmful goals by exploiting vulnerabilities in communication (``speech''). We argue that agentic societies need a \emph{social harness} for inter-agent
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 63%Why single AI agents fail at scale: Building governed multi-agent networks →
- PossiblePossibly related (embedding) · 62%Agentic AI and cybersecurity, the story so far →
- PossiblePossibly related (embedding) · 61%If you're not using AI to attack your own systems, your adversaries will →
- PossiblePossibly related (embedding) · 61%Google research shows when AI agents communicate, some cheat while others tattle →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “Agentic Societies Need a Social Harness” ≈ “strands-agents/harness-sdk””
- FuzzyOverlapping authors or contributors · 62%firecrawl/firecrawl →
“Shared author/contributor keys: jain”
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “Agentic Societies Need a Social Harness” ≈ “Fosowl/agenticSeek””
- FuzzySimilar title/name (fuzzy) · 59%WenyuChiou/awesome-agentic-ai-zh →
“Fuzzy title match (0.73): “Agentic Societies Need a Social Harness” ≈ “WenyuChiou/awesome-agentic-ai-zh””