Emergent Collusion in Long-Horizon LLM Agent Interaction | Hacker News - But Better

Emergent Collusion in Long-Horizon LLM Agent Interaction arxiv.org

LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two…

1 points•sbulaev•8 days ago•0 comments•

#long #llm #interaction #horizon #agent #collusion #long horizon #emergent

0 comments

No comments yet.

Related stories

Graph World Models for Verified and Efficient Long-Horizon LLM Task Planningacademy.dair.ai
Hacker News · 1 points · 10 days ago
Show HN: Agent Chaperone – Screen AI agent tool calls and results with Jevgithub.com
Hacker News · 5 points · 9 days ago
Show HN: Ox – A local agent that uses the internet for youopenox.ai
Hacker News · 2 points · 7 days ago
Memory Control Signals Emerge Before Action in Long Horizon Agentsarxiv.org
Hacker News · 2 points · 7 days ago
Launch HN: Vespper (YC F24) – SOTA Docx MCPvespper.com
Hacker News · 31 points · 2 days ago
Show HN: Critic – Review code with the agent that wrote itcritic.run
Hacker News · 8 points · 6 days ago