MATS Fellow:
Kai Fronsdal
Authors:
Kai Fronsdal, David Lindner
Citations
Abstract:
We propose a suite of tasks to evaluate the instrumental self-reasoning ability of large language model (LLM) agents. Instrumental self-reasoning ability could improve adaptability and enable self-modification, but it could also pose significant risks, such as enabling deceptive alignment. Prior work has only evaluated self-reasoning in non-agentic settings or in limited domains. In this paper, we propose evaluations for instrumental self-reasoning ability in agentic tasks in a wide range of scenarios, including self-modification, knowledge seeking, and opaque self-reasoning. We evaluate agents built using state-of-the-art LLMs, including commercial and open source systems. We find that instrumental self-reasoning ability emerges only in the most capable frontier models and that it is highly context-dependent. No model passes the the most difficult versions of our evaluations, hence our evaluation can be used to measure increases in instrumental self-reasoning ability in future models. We open-source our evaluations at https://github.com/kaifronsdal/Self-Reasoning-Evals.
What Should Frontier AI Developers Disclose About Internal Deployments?
Authors:
Jacob Charnock, Raja Moreno, Justin Miller, William L. Anderson
Date:
April 24, 2026
Citations:
Where is the Mind? Persona Vectors and LLM Individuation
Authors:
Pierre Beckmann
Date:
April 20, 2026
Citations:
The MATS Program is an independent research and educational initiative connecting emerging researchers with mentors in AI alignment, governance, and security.
Each MATS cohort runs for 12 weeks in Berkeley, California, followed by an optional 6–12 month extension in London for selected scholars.