Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 25, 2026

From Pairs To Coalitions: Extending Information-Theoretic Collusion Detection To Multi-Agent Games

Chae Eun Lee, Fabian Rosdalen, Peter Samodelkin, Yasin Edin · Team 29th-ML4Gang-Summit

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

Read the report

Report: From Pairs To Coalitions: Extending Information-Theoretic Collusion Detection To Multi-Agent Games

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

We study information-theoretic approaches to detect collusion and coalition members in a multi-player rock-paper-scissors game testbed with coordinated collusion. We compare a net-influence baseline with four methods that combine conditional mutual information, standardized against shuffled actions, with connected components, Louvain communities, likelihood-based search or average-$z$ growth. Across 2,800 coalition and 400 honest scripted test games, the ML decoder achieved the highest recall (81.71%), while Louvain most often recovered the exact coalition groups (73.29%). The graph methods could recover two separate coalitions that the single-group methods could not represent. Experiments with Qwen2.5:14B extend the evaluation to instructed model-generated coordination. The results motivate the use of action-based audits with information-theoretic approaches for detecting colluding agents.

Reviews

Judging this Sprint?

Review “From Pairs To Coalitions: Extending Information-Theoretic Collusion Detection To Multi-Agent Games”

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 is a useful benchmark contribution with clear follow-up experiments.

Cite this project

@misc{lee2026from,
  title = {{From Pairs To Coalitions: Extending Information-Theoretic Collusion Detection To Multi-Agent Games}},
  author = {Chae Eun Lee and Fabian Rosdalen and Peter Samodelkin and Yasin Edin},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/from-pairs-to-coalitions-extending-informationtheoretic-collusion-detection-to-multiagent-games-wqzo}},
  url = {https://apartresearch.com/sprints/projects/from-pairs-to-coalitions-extending-informationtheoretic-collusion-detection-to-multiagent-games-wqzo}
}

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