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

Remove the Message, Catch the Colluder

Aradhya Goel · Team Anti-colluders

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

Read the report

Report: Remove the Message, Catch the Colluder

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

Detectors that only watch what agents do will flag any agents that behave alike. So they cannot tell agents that coordinate by talking from agents that simply want the same thing. We detect collusion by intervening instead. We replay a game between AI agents and replace one agent’s message with a version that points to the opposite choice. Then we check whether another agent’s decision changes. We test this in a four-agent voting game with GPT-5.6. We compare a colluding pair with two agents who share the same hidden goal but cannot communicate. Replacing messages finds the colluding pair in every run and raises no false alarms. Standard detectors that measure how similar the agents’ votes are fail to tell the two cases apart. We then perform the same intervention inside an open model. We leave the message text unchanged but push the model’s internal reading of it toward the opposite choice. This works only early in the model. There it picks out the colluding pair as well as rewriting the text does, while a random push does nothing. Our method also offers a way to test a rule that Rose et al. (2026) include in their definition of collusion but could not check. The rule says that collusion should stop when the messages are taken away.

Reviews

Judging this Sprint?

Review “Remove the Message, Catch the Colluder”

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 idea of changing a message and replaying an agent's decision is a simple and interesting way to test influence. The controls and fixes for potential replay issues are good strengths. My main concern is that following a teammate's useful message could produce the same signal as collusion. The experiments are also fairly small and use simplified settings. Testing more realistic scenarios, including honest cooperation and emergent collusion, would make the results much more convincing.

Cite this project

@misc{goel2026remove,
  title = {{Remove the Message, Catch the Colluder}},
  author = {Aradhya Goel},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/remove-the-message-catch-the-colluder-44zw}},
  url = {https://apartresearch.com/sprints/projects/remove-the-message-catch-the-colluder-44zw}
}

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