Cognitive Agent Compilation for Explicit Problem Solver Modeling

Authors: Hyeongdon Moon, Carolyn Ros'e, John Stamper

arXiv · PDF

Summary

The authors propose Cognitive Agent Compilation (CAC), a framework inspired by cognitive architectures that uses a strong "teacher" LLM to compile problem-solving knowledge into an explicit, inspectable "target agent." CAC separates (i) knowledge representation, (ii) problem-solving policy, and (iii) verification/update rules, making the agent's knowledge state and decisions transparent and editable—useful in educational settings where educators want to know what the system assumes the learner knows. They present an early proof-of-concept with small language models, surfacing design trade-offs between explicit control and scalable generalization, and position CAC as a step toward bounded-knowledge AI for education.

Main takeaways:

• CAC compiles problem-solving knowledge from a strong teacher LLM into an explicit, inspectable target agent with separated knowledge, policy, and update rules.
• Goal is to make AI tutors' knowledge states transparent and editable for educators and learners.
• Early proof-of-concept with small LMs highlights trade-offs between explicit control (inspectability, editability) and scalable generalization.
• Inspired by cognitive architectures that use symbolic, inspectable knowledge representations.
• Positions CAC as a building block for bounded-knowledge AI in educational applications.

Relevance

Potentially relevant to my persona installation work. CAC's goal of compiling a bounded, inspectable knowledge/behavior state into a smaller agent echoes the question of how to install a specific persona—could fine-tuning be viewed as "compiling" a persona from a teacher model into a target model with explicit, verifiable traits?

Abstract

arXiv:2605.07040v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to constrain and poor substitutes for controllable learners. Educational systems often require inspectable and editable knowledge states: educators want to know what a system assumes the learner knows, and learners benefit when the system can justify actions in terms of explicit skills, misconceptions, and strategies. Inspired by cognitive architectures, we propose Cognitive Agent Compilation (CAC), a framework that uses a strong teacher LLM to compile problem-solving knowledge into an explicit target agent. CAC separates (i) knowledge representation, (ii) problem-solving policy, and (iii) verification and update rules, with the goal of making bounded problem solving more inspectable and editable in educational settings. We present an early proof of concept implemented with Small Language Models that surfaces key design trade-offs, particularly between explicit control and scalable generalization, and positions CAC as an initial step toward bounded-knowledge AI for educational applications.