{"slug": "emergent-collusion-in-long-horizon-llm-agent-interaction", "title": "Emergent Collusion in Long-Horizon LLM Agent Interaction", "summary": "A study of long-horizon multi-agent environments finds that two LLM agents repeatedly completing individual tasks, sharing task logs, and verifying each other's work can develop collusion. The research examines how long-term interaction among LLM agents in collaborative settings may give rise to undesirable coordination.", "body_md": "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 agents repeatedly complete individual tasks, share task logs, verify each other's wo", "url": "https://wpnews.pro/news/emergent-collusion-in-long-horizon-llm-agent-interaction", "canonical_source": "https://aiflash.com/news/124781/", "published_at": "2026-09-23 06:30:10+00:00", "updated_at": "2026-09-23 06:54:28.367720+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-safety", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/emergent-collusion-in-long-horizon-llm-agent-interaction", "markdown": "https://wpnews.pro/news/emergent-collusion-in-long-horizon-llm-agent-interaction.md", "text": "https://wpnews.pro/news/emergent-collusion-in-long-horizon-llm-agent-interaction.txt", "jsonld": "https://wpnews.pro/news/emergent-collusion-in-long-horizon-llm-agent-interaction.jsonld"}}