Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.20281 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914412132040704 |
|---|---|
| author | Keppo, Jussi Li, Yuze Tsoukalas, Gerry Yuan, Nuo |
| author_facet | Keppo, Jussi Li, Yuze Tsoukalas, Gerry Yuan, Nuo |
| contents | Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20281 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Fragility of AI Agent Collusion Keppo, Jussi Li, Yuze Tsoukalas, Gerry Yuan, Nuo Computer Science and Game Theory Artificial Intelligence 91A20, 91B24, 68T05 J.4; I.2.11; K.4.1 Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity. |
| title | On the Fragility of AI Agent Collusion |
| topic | Computer Science and Game Theory Artificial Intelligence 91A20, 91B24, 68T05 J.4; I.2.11; K.4.1 |
| url | https://arxiv.org/abs/2603.20281 |