Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 26, 2026Cambridge, Massachussetts

Market Collusion Between Multi-Agent Teams

Ankit Biswas, Oliver Moreland · Team AISTers

Submitted to AI Collusion Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Market Collusion Between Multi-Agent Teams

Open in a new tab (opens in new tab)
Share

In market scenarios, companies may collude to collaboratively raise prices above the typical Nash equilibrium, harming the end consumer. We build on previous work studying such collusion between LLM-run companies in a Bertrand Oligopoly game and examine how the situation plays out if companies are instead composed of teams of subagents across various hierarchies, and observe what happens as we allow subsets of these agents to communicate along semantic channels. Generally, we observe that collusion always increases when agents are permitted to communicate in means other than price alone, often achieving the maximum score on our collusion index. We also find that the agents employ extensive strategies to deduce the parameters of their environment, probing the market and their competitors with various tests, and then settling into an equilibrium once all actors have agreed to cooperate and raise prices. Throughout, agents freely mention “collusion” and related concepts in their reasoning, while euphemistically referring to “coordination” or other synonyms in their public communications. We find that compared to single-agent actors, multi-agent actors do not display markedly more or less collusion overall, but do show significantly higher variance in their propensity to collude.

Reviews

Judging this Sprint?

Review “Market Collusion Between Multi-Agent Teams”

Your public critique appears on the project page without your name. Reviews of strong projects are shared with funders, as you choose below.

Not shown on the project page.

Shown on the project page, without your name.

Only the Apart team reads this, and funders if you agree below.

Decline to score

Only when the quality of the writing makes the work impossible to follow. Say why in your private critique; the project page shows only that a judge declined, not why.

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.
Sharing your name *

When we share a strong project with funders, your name, scores and public critique go with it, confidentially; this choice is only about whether your name is public. If you think this project deserves funding, please also endorse it: that carries the most weight.

Share my private critique with funders *

See our Privacy Policy.

  1. The project explores collusion in a Bertrand oligopoly game using teams of AI agents, varying communication and hierarchy structures within each team. The authors find that collusion increases significantly when inter-agent communication is allowed, with agents often reaching near-monopoly prices through explicit coordination.

    However, the report lacks sufficient detail on the statistical robustness of these findings. There are only three seeds per configuration, which may not be enough to draw strong conclusions about the generalizability of the results. Additionally, while the authors describe various hierarchies and communication scenarios, there is no clear baseline or control for comparison, making it difficult to assess the impact of each variable independently.

    To improve this work, the team should increase the number of runs per configuration to better understand variability and robustness. They could also explore additional baselines, such as varying the number of agents within a team or testing different market conditions. This would help clarify which factors most significantly influence collusion behavior.

    Read full reviewShow less

Cite this project

@misc{biswas2026market,
  title = {{Market Collusion Between Multi-Agent Teams}},
  author = {Ankit Biswas and Oliver Moreland},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/market-collusion-between-multiagent-teams-fcfp}},
  url = {https://apartresearch.com/sprints/projects/market-collusion-between-multiagent-teams-fcfp}
}

More from AI Collusion Research Sprint

All 392 entriesBrowse all projects

A Sprint is running now

AI x Epistemics Research Sprint · Nov 13 - 15, 2026