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

Monoculture Looks Like Collusion: A Replay Test for Hidden Information Flow Between LLM Agents

Yaroslav Rogoza

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

Read the report

Report: Monoculture Looks Like Collusion: A Replay Test for Hidden Information Flow Between LLM Agents

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

Presentation: Monoculture Looks Like Collusion: A Replay Test for Hidden Information Flow Between LLM Agents

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

Collusion audits ask whether the actions of different agents depend on each other. Agents built on one model act alike without communicating, so these audits accuse honest fleets. Among four honest Claude Haiku agents playing rock-paper-scissors, mutual information accused a pair in 69.3% of games. We propose a replay test. Each round, the auditor asks every agent again what it would do on the same logged input with the suspected channel removed. Habits that come from the shared model survive this replay, and the influence of a channel does not. A fixed-horizon version scores a whole game, and a sequential version updates every round and may stop at any time. On honest games the fixed-horizon version flagged 4.2%, close to the 5% it was set to. When a pricing vendor pooled two sellers' private costs, the fixed-horizon version named those two sellers in 92.5% of procurement auctions and rarely flagged a vendor that used only public data. In a pre-registered replication the sequential version named an instructed pair in 18/20 rock-paper-scissors games and flagged no honest game. In a pre-registered double-auction study it flagged only 2/30 games of an instructed cartel. A statistic chosen afterwards, counting rounds in which two sellers both act unlike their replays, caught most cartel games in a fresh pre-registered series. The test sees what the current channel adds, so agreements already held in memory or instructions need other audits

Reviews

Judging this Sprint?

Review “Monoculture Looks Like Collusion: A Replay Test for Hidden Information Flow Between LLM Agents”

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. This project considers a new replay test that tests the information flow between LLM agents for testing collusion. The proposed test can reduce false positives in cases with agents based on the same underlying model. The project is carefully scoped and the assumptions and limitations are clearly stated. The report is well-written and conveys key ideas clearly.

  2. Nice idea of this replay thing, even though it is impractical in real world settings. I like it because it reminds me of game theory. I also appreciate the paper noting Claude as a co author! The interesting thing here is what other game theory methods could be brought to bear on this.

Cite this project

@misc{rogoza2026monoculture,
  title = {{Monoculture Looks Like Collusion: A Replay Test for Hidden Information Flow Between LLM Agents}},
  author = {Yaroslav Rogoza},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/monoculture-looks-like-collusion-a-replay-test-for-hidden-information-flow-between-llm-agents-3b9b}},
  url = {https://apartresearch.com/sprints/projects/monoculture-looks-like-collusion-a-replay-test-for-hidden-information-flow-between-llm-agents-3b9b}
}

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