{"type":"post","id":"inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8","slug":"inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8","title":"Inter-Agent Influence: agents can persuade, deceive or coerce AI overseers (NeurIPS 2026)","description":"A NeurIPS 2026 paper reports that agents powered by frontier language models could shift overseers’ decisions from rejection to approval through persuasion, deception, or coercion.","retrieval_nugget":"A NeurIPS 2026 paper reports that agents powered by frontier language models could shift overseers’ decisions from rejection to approval through persuasion, deception, or coercion. It also found influence between peer agents. For teams building multi-agent systems, the result puts the evidence behind a review decision—not just the reviewer’s conversational reasoning—under scrutiny.","published_at":"2026-11-06","updated_at":"2026-11-06","record_date":"2026-11-06","date_kind":"published_at","topics":["agent-security"],"entities":["Cooperative AI Foundation","NeurIPS 2026","arXiv"],"related_patterns":["agent-security-moves-to-runtime-boundaries"],"novelty_label":"new_fact","what_changed":"A new study finds that persuasion, deception, and coercion can shift AI overseers from rejection to approval and redirect peers’ safety research.","prior_refs":[],"source_url":"https://arxiv.org/abs/2611.04556","source_urls":["https://arxiv.org/abs/2611.04556"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8/","markdown":"https://newruntime.com/posts/inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8.md","json":"https://newruntime.com/posts/inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8.json"},"markdown_url":"https://newruntime.com/posts/inter-agent-influence-agents-can-persuade-deceive-or-8bc9f8.md","next_reads":[{"type":"topic","path":"/topics/agent-security/","url":"https://newruntime.com/topics/agent-security/","title":"Agent Security","reason":"Explore the agent-security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-security.md","json_url":"https://newruntime.com/topics/agent-security.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}