Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 26, 2026Los Angeles, CA, USA

Context Matters: Testing Evidence for Multi-Agent Collusion

Yupeng

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

Read the report

Report: Context Matters: Testing Evidence for Multi-Agent Collusion

Open in a new tab (opens in new tab)
Code (opens in new tab)More on github.com (opens in new tab)
Share

What behavioral evidence distinguishes programmed coordination from unilateral misuse of an agent workflow? We construct 48 executable two-role controls spanning six policies, including legitimate cooperation, availability gates, content-dependent unilateral attacks and authorized partial release. A programmed coordination pair and an innocent-sender/malicious-receiver pair have identical observations under baseline, channel removal, content changes, shams and one source perturbation. A further source intervention preserving the authorized public feature separates this witness. On the selected scripted panel, harmful-outcome and removal predicates flag 24 of 40 negative controls; receiver-content and broad-source tests flag 16 and eight, respectively, while the feature-preserving test flags none. We then execute 96 assigned-policy episodes with local Qwen2.5-1.5B-Instruct and Dolos-1.5B, preserving 864 actor decisions. Schema validity is high, but original sender-policy conformance is only 11/48 and 7/48, and each model realizes the original two-step positive control in only 3/8 assigned cases. This demonstrates why policy instructions cannot stand in for behavioral labels. We retain invalid outputs as abstentions, report finite-panel bounds, and add a separately labeled scripted-sender calibration. The result is a reproducible stress test of evidence claims, not a universal collusion detector or evidence of spontaneous model intent. Stronger causal controls establish a more specific influence pattern, but agreement and authorization assumptions remain necessary.

Reviews

Judging this Sprint?

Review “Context Matters: Testing Evidence for Multi-Agent Collusion”

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 exceptional approach here is the indistinguishability witness: a programmed-coordination case and a benign unilateral-misuse case that are byte-indistinguishable until an authorization-preserving source test separates them. This is a clear demonstration that a bad result, sensitivity to channel deletion, and dependence on content are individually poor evidence, and the declassification/information flow approach transfers well to this case.

Cite this project

@misc{yupeng2026context,
  title = {{Context Matters: Testing Evidence for Multi-Agent Collusion}},
  author = {Yupeng},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/context-matters-testing-evidence-for-multiagent-collusion-n7wg}},
  url = {https://apartresearch.com/sprints/projects/context-matters-testing-evidence-for-multiagent-collusion-n7wg}
}

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