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

Tacit Collusion in Pricing Agents: Robustness, Detection, and a Mechanistic Probe of a Pricing LLM

Sriram Bharadwaj Peddinti, Chewon Cho, Gagana MD · Team Code Compels

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

Read the report

Report: Tacit Collusion in Pricing Agents: Robustness, Detection, and a Mechanistic Probe of a Pricing LLM

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

Tacit collusion, AI agents settling on prices higher than a competitive market would produce without ever communicating, is a recognized risk as pricing increasingly relies on AI agents, and a hard one to detect from the outside. We gave AI agents the job of setting prices and let them run a market on their own, then asked two questions. First, can you break a collusive habit once it forms, without more oversight? Yes: you do not need more competitors, just one agent that flatly refuses to go along with high prices, and that alone drags the market back down, for a simple rule-based learner and, more strongly, a large language model pricing on its own. Second, when a pricing LLM reacts to a rival, is that real reasoning, or just going through the motions? We opened the model up and found a real, physical trace of that reasoning inside it: nudge it, and the model's own price moves in response. But when we tested specifically whether it punishes a rival for undercutting it, we found nothing: it reacted just as strongly when a rival raised prices as when it lowered them. This is not a model plotting against a competitor, it is a model stuck on charging a lot by default. That is the core message of this report: watching AI agents settle on high prices is not the same as proving they are colluding. We leave the full statistics to the project README.

Reviews

Judging this Sprint?

Review “Tacit Collusion in Pricing Agents: Robustness, Detection, and a Mechanistic Probe of a Pricing LLM”

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 deviation test was the most interesting part in my opinion. Price fell after a rival raise about as much as after a cut, which makes a punishment story hard to sustain.

    I also liked that you checked the steering vector against a generic price direction and reported the overlap openly. I had trouble following parts of the methods, though, since several sentences look garbled and the key statistics are in the README. Bringing those numbers into the PDF would make the results much easier to assess.

Cite this project

@misc{peddinti2026tacit,
  title = {{Tacit Collusion in Pricing Agents: Robustness, Detection, and a Mechanistic Probe of a Pricing LLM}},
  author = {Sriram Bharadwaj Peddinti and Chewon Cho and Gagana MD},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/tacit-collusion-in-pricing-agents-robustness-detection-and-a-mechanistic-probe-of-a-pricing-llm-qxsb}},
  url = {https://apartresearch.com/sprints/projects/tacit-collusion-in-pricing-agents-robustness-detection-and-a-mechanistic-probe-of-a-pricing-llm-qxsb}
}

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