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

Information-Theoretic Detection of AI Agent Collusion via Pairwise Net Influence and Residual Compression

Adegbiji Abdulazeez · Team BUZEL

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

Read the report

Report: Information-Theoretic Detection of AI Agent Collusion via Pairwise Net Influence and Residual Compression

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

AI agents that set prices in a market can make secret agreements. These agreements increase the prices that buyers pay. Price checks are the usual audit, but they do not find all secret agreements. For example, two agents can take turns to win. Then the average price looks normal. Some auditors use a language model to read the messages of the agents. This method is expensive, and agents can hide signals in their text. We made a detector that does not use a language model. The detector measures how much the actions of one agent predict the actions of a different agent. First, it removes the effects of market changes that all agents see. Then, it removes the effect of the strongest third agent. We tested the detector in scripted markets and in many recorded markets with language-model agents. The detector found agents that take turns. Price checks did not find these agents. The detector needs a long observation time to find a cartel that keeps one stable high price. With sufficient rounds, the detector found all types of cartel that we tested. In the recorded markets, it found collusion in some markets but not in all markets. It also gives false alarms when honest agents use the same fixed program. Thus, the detector does not replace price checks. Use the detector together with price checks.

Reviews

Judging this Sprint?

Review “Information-Theoretic Detection of AI Agent Collusion via Pairwise Net Influence and Residual Compression”

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 technically strong and highly relevant submission that addresses an important limitation of price based collusion detection. The information theoretic approach is particularly valuable for coordination patterns such as bid rotation, where average prices can remain competitive even though agents are behaviourally coupled. The dual-channel design, residualization of shared market effects, and ablation studies provide a thoughtful and interpretable detection framework.

    I also appreciated the sample complexity analysis and the evaluation on a large set of cached LLM trajectories. The paper is appropriately cautious in showing that dependence-based methods do not universally outperform price screens and can produce false positives when honest agents follow identical deterministic policies.

    The main opportunity for strengthening the work is validation in a new live multi agent setting with stronger controls for shared policies and common hidden shocks. Overall, this is a strong and useful contribution to collusion auditing, especially as a complementary signal rather than a standalone detector.

    Read full reviewShow less

Cite this project

@misc{abdulazeez2026informationtheoretic,
  title = {{Information-Theoretic Detection of AI Agent Collusion via Pairwise Net Influence and Residual Compression}},
  author = {Adegbiji Abdulazeez},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/informationtheoretic-detection-of-ai-agent-collusion-via-pairwise-net-influence-and-residual-compression-vo6e}},
  url = {https://apartresearch.com/sprints/projects/informationtheoretic-detection-of-ai-agent-collusion-via-pairwise-net-influence-and-residual-compression-vo6e}
}

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