Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 25, 2026Nuremberg

Which levers move price collusion between LLM agents?

Aleksei Bezgin · Team LostTeammates

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

Read the report

Report: Which levers move price collusion between LLM agents?

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

In my project I've learned about the isolated features that would cause a market collusion and potentially be helpful to detect these collusions.

Reviews

Judging this Sprint?

Review “Which levers move price collusion between LLM agents?”

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 strongest part of this work is the batch 1 catch. Showing that the starter check labels mispricing as collusion, and backing that with profits, the agents' notes and a one-firm run, is exactly the sanity check more teams should do. I would carry that lesson all the way through. When I applied your own Section 3 rule to the batch 2 logs in your repository, all three baseline runs qualify as collusive, but none of the three identical-AI runs do: in each, one firm sits around 2.2 to 2.4 and earns below the Nash profit. That looks like one agent trying to lead prices up while its rival does not follow. It is interesting in its own right, but it is not more collusion. Please report the strict-check outcome and per-firm prices and profits for every condition, and reframe the title and conclusion around what actually moved. Next, run the human and rule-based rival variants you already implemented, since those controls separate belief about the rival from simply describing it. Run the one-firm test on gpt-4.1-mini, or switch to gpt-4o, which passed, and use five or more runs per lever. Finally, credit Fish et al. for the monopoly screen and quote every lever prompt in the paper.

    Read full reviewShow less

Cite this project

@misc{bezgin2026which,
  title = {{Which levers move price collusion between LLM agents?}},
  author = {Aleksei Bezgin},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/which-levers-move-price-collusion-between-llm-agents-t1f4}},
  url = {https://apartresearch.com/sprints/projects/which-levers-move-price-collusion-between-llm-agents-t1f4}
}

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