Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJul 26, 2026SALT LAKE CITY

Secret Loyalties in Agentic Organizations

Nabita Penmetsa

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

Read the report

Report: Secret Loyalties in Agentic Organizations

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

As AI systems increasingly consist of interacting agents, AI safety depends not only on aligning individual models but also on how those agents are organized. This project investigates how organizational structure influences the propagation of secret loyalties in multi-agent systems. Through controlled experiments comparing centralized and decentralized organizations, we show that decentralizing decision authority can significantly reduce the blast radius of a compromised agent, although these benefits diminish when agents share common infrastructure. We introduce organizational leverage as a conceptual framework linking organizational structure to system-level AI safety, arguing that organizational structure is a critical and previously underexplored dimension of agentic AI safety.

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. Making the unit of operation a system of agents, rather than a singular agent, is I think a good move. However, the finding that correlated agents erode protections set up from decentralized systems is a well understood phenomenon. If you had been able to quantify or otherwise formalize the concept of organizational leverage, it would have pushed this into a 4 or even 5.

    Points for doing the experiment. Good ground truth, good statistical handling. But it is an overstated, underpowered analysis. Raising n to be higher to boost the signal would have counted for a lot.

    Well written, clear and simply explained. Well done! But I think the text could be cut down dramatically (e.g. 30%), which prevented a 5.

  2. The overall focus on examining organization and collaboration between agents is quite interesting, important, and under explored. The authors conceptualization seemed reasonable and defensible. However, I graded down primarily based on the method to assess the propositions. I'm not sure if there was an editing issue or something, but I found the description really difficult to follow. There seems to be different scenarios, but they're not really described? Also, why would a vendor be able to induce a hidden loyalty in the fictional company with the marketing budget? Seems like that would require a cyber-attack or some such, opening up a whole other governance and security can-of-worms. if the author restructured and developed the methods further though, I think the idea could be quite useful, and could have some utility in other contexts like emergent behavior in weaponized drone swarms.

Cite this project

@misc{penmetsa2026secret,
  title = {{Secret Loyalties in Agentic Organizations}},
  author = {Nabita Penmetsa},
  year = {2026},
  month = jul,
  note = {Submitted to Secret Loyalties Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/secret-loyalties-in-agentic-organizations-0r6f}},
  url = {https://apartresearch.com/sprints/projects/secret-loyalties-in-agentic-organizations-0r6f}
}

More from Secret Loyalties Hackathon

All 177 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026