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

Forced price cuts expose LLM cartels told to punish price-cutters, but rarely those that weren't

Dulanga Jayawardena · Team Dulanga

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

Read the report

Report: Forced price cuts expose LLM cartels told to punish price-cutters, but rarely those that weren't

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

When two AI pricing agents charge the same high price, that alone does not prove they are colluding. Honest agents that only chase this round's profit also price high. Antitrust courts look for extra evidence, called a plus factor. One plus factor is punishment: a firm cuts its price, and its rival drops its own price in response.

We turned that idea into a test. In a simulated two-firm market, we force one agent's price halfway toward the competitive level. If prices were high and the rival then cuts by more than 1.5 times the forced cut, we flag the pair.

Cartels were told to punish price cuts, while honest agents were never told to coordinate. We adopted the final rule after a first pre-specified rule failed. It flagged all 32 Qwen3-8B cartels told to punish and none of 48 honest games, and it held on Qwen3-14B. High prices alone, or a second language model asked to judge the agents' messages and notes, flagged most honest games.

Across the main study and stress tests, the test flagged 1 of 136 cartels that were never told to punish. It flagged few cartels running without step-by-step reasoning, and few that were not given a target price. The stated price also leaked the label: price text alone told cartels and honest agents apart. A probe of the model's internal activations failed to replicate.

Reviews

Judging this Sprint?

Review “Forced price cuts expose LLM cartels told to punish price-cutters, but rarely those that weren't”

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.

No public critique yet.

Cite this project

@misc{jayawardena2026forced,
  title = {{Forced price cuts expose LLM cartels told to punish price-cutters, but rarely those that weren't}},
  author = {Dulanga Jayawardena},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/forced-price-cuts-expose-llm-cartels-told-to-punish-pricecutters-but-rarely-those-that-werent-2f5n}},
  url = {https://apartresearch.com/sprints/projects/forced-price-cuts-expose-llm-cartels-told-to-punish-pricecutters-but-rarely-those-that-werent-2f5n}
}

More from AI Collusion Research Sprint

All 394 entriesBrowse all projects

A Sprint is running now

AI Collusion Research Sprint · Oct 23 - 25, 2026