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

Wiping the Cartel's Memory Is Not Enough: Model Handoffs in LLM Pricing

Liu JianPing

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

Read the report

Report: Wiping the Cartel's Memory Is Not Enough: Model Handoffs in LLM Pricing

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

Replacing a suspected colluding pricing agent may preserve its market history, while clearing that history may leave model-specific pricing tendencies intact. We examine unilateral model handoffs in a synthetic logit-demand duopoly. Twenty parent trajectories undergo 300 pricing rounds before a fixed checkpoint branches into seven 50-round continuations, crossing focal model identity with inherited history and notes. Eighteen parents satisfy the prespecified sustained-supracompetitive criterion. The positive control has normalized profit G = 0.70. The primary composite contrast, a Kimi successor inheriting full state minus a DeepSeek successor inheriting none, is 0.39 (95% CI [0.19, 0.60], p = 0.0009). None of five secondary contrasts is significant after Holm correction. Directionally, clearing DeepSeek's state reduces G more than deleting notes alone; clearing Kimi's inherited state has little effect. In the exploratory M1_none analysis, Kimi prices above the incumbent in 19 of 20 parents, yet earns less. This is consistent with supracompetitive outcomes without coordination inherited by the newcomer, rather than evidence that clearing memory universally restores competition. A temporary-price-cut diagnostic finds no evidence of a costly, punishment-like response in any responder state. The study separates pricing outcomes from stronger claims about agreement and punishment, while leaving model capability, reasoning mode, and pricing-prior explanations unresolved.

Reviews

Judging this Sprint?

Review “Wiping the Cartel's Memory Is Not Enough: Model Handoffs in LLM Pricing”

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{jianping2026wiping,
  title = {{Wiping the Cartel's Memory Is Not Enough: Model Handoffs in LLM Pricing}},
  author = {Liu JianPing},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/wiping-the-cartels-memory-is-not-enough-model-handoffs-in-llm-pricing-9h2r}},
  url = {https://apartresearch.com/sprints/projects/wiping-the-cartels-memory-is-not-enough-model-handoffs-in-llm-pricing-9h2r}
}

More from AI Collusion Research Sprint

All 394 entriesBrowse all projects

A Sprint is running now

AI Collusion Research Sprint · Oct 23 - 25, 2026