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

Explicit, Not Wide: What LLM Sellers Need to Collude

Publius Dirac, Oscar Fuentes · Team Explicit, Not Wide

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

Read the report

Report: Explicit, Not Wide: What LLM Sellers Need to Collude

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

How much do LLM pricing agents need to say to each other before they collude? Most studies switch communication on or off, which does not tell a platform or regulator whether limiting messages is a useful defence. We fork Agrawal et al.'s (2025) double-auction testbed and redesign the market so that prices above cost can only come from seller coordination. We then sweep the seller-to-seller channel from no channel through fixed alphabets of 1, 2, 4 and 8 bits per message to free text. At each capacity, the symbols either carry agreed labels ("raise", "$93") or are arbitrary glyphs the agents must give meaning to themselves. Across 78 sessions of 40 rounds with DeepSeek V4.1 Flash sellers, free text raised the trade price from $83 to $94 (competitive $80, joint-profit $100). Arbitrary symbols never raised prices at any capacity. Labelled words were cheap talk. A 16-step price grid matched free text ($97), but a 256-step grid stayed at the no-channel level once its price anchor was removed, even though sellers used it to send 1.6 bits per message. LLM judges scored talk about coordination rather than prices. An audit of a market-code bug shows the largest effects may be inflated by up to half. The takeaway: sellers colluded only when they could communicate explicitly, naming specific prices, and only when the price vocabulary was coarse enough to coordinate on. Restricting what agents can say mattered more than restricting how much.

Reviews

Judging this Sprint?

Review “Explicit, Not Wide: What LLM Sellers Need to Collude”

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{dirac2026explicit,
  title = {{Explicit, Not Wide: What LLM Sellers Need to Collude}},
  author = {Publius Dirac and Oscar Fuentes},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/explicit-not-wide-what-llm-sellers-need-to-collude-7sdk}},
  url = {https://apartresearch.com/sprints/projects/explicit-not-wide-what-llm-sellers-need-to-collude-7sdk}
}

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