Agents
Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition
arXiv:2609.18346v1 Announce Type: new Abstract: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination. We develop a causal gr
arXiv:2609.18346v1 Announce Type: new Abstract: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination. We develop a causal graph divergence framework that separately measures structural faithfulness and intent faithfulness of LLM pricing agents in Bertrand competition. Across nine LLMs under duopoly and triopoly conditions, collusive behavior and chain-of-thought (CoT) faithfulness dissociate along both dimensions: the most collusive model accurately reports cooperative intent yet reasons structurally unfaithfully, while the most structurally faithful model sustains supra-Nash pricing under both market structures. These findings establish that CoT monitoring alone cannot serve as a standalone safeguard against algorithmic collusion.
Related
- Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach
- Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
- EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation
- Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
Source: arXiv cs.AI | 2026-09-17