Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition
cs.AI, cs.CL
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 20 pages, Accepted to Findings of EMNLP 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination.
Terminology
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.
Sources
- Reasoning Models Don't Always Say What They Think
- Algorithmic Collusion by Large Language Models
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection