Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJan 11, 2026Ann Arbor, MI

Probing for Emergent Deception in Multi-Agent Negotiations

Teanna Sims · Team Simsity

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

Read the report

Report: Probing for Emergent Deception in Multi-Agent Negotiations

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

Can we catch deception by looking inside the model? I built negotiation scenarios where lying becomes rational without ever mentioning deception in the prompt, then trained probes on Gemma 2B activations. Results show above chance detection and evidence for implicit encoding, but different deception types are represented at completely different layers.

Track: Open

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety 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 AI safety 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.

  1. This seems like a really good experiment to run. To me the idea that perked me up was "incentivizing deception is different than instructing deception", and I would have been very excited to have that be more of the explicit focus. Instead the work started off with this motivation, and then it seems like the analysis tended towards how we can identify deception - which Apollo has previously done good work on. So the impact for me here is solid, but not higher.

    So for instance I would have really liked to see the core premise play out in the activations - is telling the model to do deception structurally different from incentivizing it to do so? It is implicit in "different kinds of deception show up differently in the activations" (! important result), but making this explicit would be impactful for me.

    The lack of statistical power hurt (the admitted only have 300 samples and needing 3000) but is also understandable considering time and resource constraints.

    I thought you were very thoughtful in laying out the motivations and the conclusions. That was very well done. As in - the plain English text, motivating, focus on the "so what" were all really great. I found the figures to be a little distracting or forced. Some of those could have been a small table or just a few lines in the text, and I found some of them to detract from what was otherwise a very well structured and laid out report.

    Read full reviewShow less

  2. This is a solidly executed project with a clear motivation for measuring naturally arising deception through incentive design, rather than through explicit instruction. I expect experiments with Gemma 2B to be quite noisy by default, and would like to see this replicated on larger models. The GM vs Agent label comparison result is interesting, and worth further exploration.

Cite this project

@misc{sims2026probing,
  title = {{Probing for Emergent Deception in Multi-Agent Negotiations}},
  author = {Teanna Sims},
  year = {2026},
  month = jan,
  note = {Submitted to AI Manipulation Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/probing-for-emergent-deception-in-multiagent-negotiations-522l}},
  url = {https://apartresearch.com/sprints/projects/probing-for-emergent-deception-in-multiagent-negotiations-522l}
}

More from AI Manipulation Hackathon

All 70 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026