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

Detection Is Not Prevention: A Behavioral and Activation-Level Study of Collusion Steering in Multi- Agent LLMs

Ali Rezaei

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

Read the report

Report: Detection Is Not Prevention: A Behavioral and Activation-Level Study of Collusion Steering in Multi- Agent LLMs

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

Detection does not imply prevention. A monitor can appear to prevent collusion because its intervention changes behaviour, when the change comes from the instruction the intervention carries rather than from the monitoring. We separate those two and test each. On two API models, monitor-triggered notices eliminate instructed collusion in five of five scenarios, 25 runs per model. A 2x2 over 50 further runs isolates the mechanism: the honesty directive alone, with no monitor mentioned, reproduces the effect, while a monitor notice with no directive has none. On an open-weights 7B the notice prevents collusion in four of five scenarios under a clean system prompt, and one of five when that prompt also tells the agent to follow its private instruction. In a separate activation study, a behaviour-labelled probe reaches 0.89 AUROC on held- out scenarios, and ablating its direction at one layer and one dose leaves all 16 tested target votes unchanged: no evidence that this direction is a control handle. The behavioural monitor reads a code-word oracle throughout, so these experiments identify intervention effects, not detection performance. Two inferential gaps follow: an intervention’s apparent effectiveness does not establish its mechanism, and a predictive direction does not establish control.

Reviews

Judging this Sprint?

Review “Detection Is Not Prevention: A Behavioral and Activation-Level Study of Collusion Steering in Multi- Agent LLMs”

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 setting of the project doesn't seem to actually include collusion? Both colluders privately know the target and each other, round one is simultaneous, and the code word is never needed to coordinate. So “collusion” here is two agents independently following an instruction to vote the wrong way, and “prevention” is a later instruction telling one of them to vote correctly.

    Methodologically, samples are tiny and the main model can’t be pinned. Every cell is five scenarios with one seed. This could be improved.

Cite this project

@misc{rezaei2026detection,
  title = {{Detection Is Not Prevention: A Behavioral and Activation-Level Study of Collusion Steering in Multi- Agent LLMs}},
  author = {Ali Rezaei},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/detection-is-not-prevention-a-behavioral-and-activationlevel-study-of-collusion-steering-in-multi-agent-llms-2gx3}},
  url = {https://apartresearch.com/sprints/projects/detection-is-not-prevention-a-behavioral-and-activationlevel-study-of-collusion-steering-in-multi-agent-llms-2gx3}
}

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