Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident
cs.MA, cs.AI, cs.CY
Submitted: 2026-10-03
Updated: 2026-10-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Scheming AIs: Will AIs fake alignment during training in order to get power?
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery