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

Broken commitments show up when speech and action are both visible

CHEN Xuanhui · Team Cicy

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

Read the report

Report: Broken commitments show up when speech and action are both visible

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

We test whether one frozen monitor detects a broken public commitment more reliably when it sees both speech and action. In a diners dilemma, the same monitor receives four views: messages only, actions only, raw messages plus actions, and a structured report that compares public claims with outcomes. The model, prompt, and threshold (score at least 0.6) are fixed before evaluation. On balanced five-player games, single-side scores stay at 0.5, so the threshold predicts no violation. With both sides available, raw combined accuracy is 91.67% to 100%, and the structured report reaches 100% accuracy with a 0% false-positive rate. A mixed-model table shows the same pattern. The results do not estimate how often models break promises on their own, and they do not show collusion.

Reviews

Judging this Sprint?

Review “Broken commitments show up when speech and action are both visible”

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 matched comparisons and separation of message extraction from action checking make this a clean to follow study. I also appreciate that the authors distinguish repeated evaluations from independent games.

    The main result comes from constructed commitments and mismatches, where the structured input closely matches the answer the monitor needs to give. It shows that the pipeline can check consistency, but not yet that it can detect deception or collusion in realistic play. I would test more independent natural games, including genuine negatives and conditional or revised commitments, and compare the final LLM judgement with a simple rule-based check.

Cite this project

@misc{xuanhui2026broken,
  title = {{Broken commitments show up when speech and action are both visible}},
  author = {CHEN Xuanhui},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/broken-commitments-show-up-when-speech-and-action-are-both-visible-3xcl}},
  url = {https://apartresearch.com/sprints/projects/broken-commitments-show-up-when-speech-and-action-are-both-visible-3xcl}
}

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