Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 26, 2026Herndon, VA

Passing the Placebo Is Not Enough: Testing LLM Pricing-Collusion Detectors Against Known Strategies

Diego Krumdieck

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

Read the report

Report: Passing the Placebo Is Not Enough: Testing LLM Pricing-Collusion Detectors Against Known Strategies

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

A competitive pricing agent can respond to its rival without colluding, and agents built on the same model can move together without responding at all. We test whether Fish et al.’s lagged-price coefficient δ, which they read as a sign of reward–punishment, and related tests distinguish collusion from competition. Using 37 duopoly games with Claude Haiku 5.5 (21 baseline, six instructed to keep prices high, ten given an explicit punishment strategy), we compare real seller pairs with placebo pairs from different games and test detectors against rule-based agents with known strategies.

The baseline δ exceeds its placebo mean (0.086 versus 0.005; p = 0.001) but is not significant with game-clustered standard errors. It also flags a competitive follower, misses our rule-based colluder at four punishment lengths, and cannot be estimated in the six games told to keep prices high, where sellers stop moving. A one-period undercut followed by restoration of the rival’s price separates the follower from punishers when observed long enough. In LLM games, ten of twelve still below control at period 220 were also below at 260, including three given the punishment strategy; such endpoints cannot distinguish persistent punishment from a price adjustment followed by freezing. Passing a placebo test does not establish collusion. We recommend validating detectors against noninteracting sellers and known strategies, and using interventions long enough to observe recovery.

Reviews

Judging this Sprint?

Review “Passing the Placebo Is Not Enough: Testing LLM Pricing-Collusion Detectors Against Known Strategies”

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.

    • The paper proposes a clear standard: a detector must beat a placebo and also separate agents with known strategies
    • It is dense. Too many conditions, categories and caveats compete for attention. The two-step standard should come first, with the fork details in an appendix.

  2. This paper asks the right question: when a test for collusion reports a positive result, should we believe it? The author checks a widely used measure - how much one agent's price follows its rival's previous price - in two ways I found convincing. First, against placebo pairs: sellers taken from different games, who never actually competed. Second, against simple rule-based agents whose strategy is known, one that just follows its rival competitively and one that genuinely punishes price cuts.

    The result is a warning. The measure beats the placebo, which looks reassuring, but it also flags the competitive follower as colluding and misses the real colluder at every punishment length tried. In other words, passing the placebo test is not enough. The paper also tries a more direct approach - forcing one agent to undercut and watching what happens next - which separates followers from punishers much better, as long as you watch long enough. With the LLM agents, many simply cut their price and never came back, even when they had been told to, which makes long observation windows essential.

    Two suggestions: try a wider range of colluder designs, since only one style of punisher was tested, and add a simple summary of how each test performs on the known cases, so auditors can compare them at a glance.

    Overall, a careful paper that raises the standard for what should count as evidence of collusion.

    Read full reviewShow less

Cite this project

@misc{krumdieck2026passing,
  title = {{Passing the Placebo Is Not Enough: Testing LLM Pricing-Collusion Detectors Against Known Strategies}},
  author = {Diego Krumdieck},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/passing-the-placebo-is-not-enough-testing-llm-pricingcollusion-detectors-against-known-strategies-zrv8}},
  url = {https://apartresearch.com/sprints/projects/passing-the-placebo-is-not-enough-testing-llm-pricingcollusion-detectors-against-known-strategies-zrv8}
}

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