SOURCE-LINKED INTELLIGENCE

Evaluating and Improving LLM Self-Modeling

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a prompt edit would change the model's final answer. To measure this capability, we introduce a benchmark that tests diverse types of self-modeling questions. Current models show non-trivial but limited self-modeling skill, and make systematic mistakes on simple counterfactual questions about their own behavior. To improve self-modeling skill, we develop a scalable synthetic-data pipeline that produces self-modeling training data, and show that reinf

Read original source ↗ Open in workspace

recordType

paper

region

Global