CORTEX: A Verified Experience Layer for Generalist Agents

2026-09-27

AI Summary

This study addresses the limitations of AI agents in validating historical solutions and adapting to environmental changes by proposing a formalized system contract coupled with an empirical verification layer. Methodologically, the approach records task conditions and proof trajectories, enabling a meta-controller to precisely replay, adapt, or synthesize prior experiences. A challenge-driven development loop is further constructed through context orchestration, validator chains, and typed storage. The core contribution lies in demonstrating that general intelligence can advance through reusable programs rather than weight updates. Evaluations across clinical and policy domains confirm perfect invariance in strategy execution, providing a preliminary yet viable pathway toward artificial general intelligence.

Abstract

An agent can solve a task today and face the same task under new facts, tools, or governing knowledge tomorrow. Most agent systems can retrieve relevant text or recall prior conversations, but they lack a principled way to decide when a previous solution is still valid, when it must be adapted, and when it should be discarded. We introduce CORTEX (Contextual Orchestration and Reuse of Task EXperience), a general AI systems framework that connects specialized agents through an external layer of verified experience. Each episode records its task conditions, source and tool state, decisive predicates, proof trace, verifier, and outcome. A meta-controller chooses exact replay, checked adaptation, fresh synthesis, or escalation. Accepted episodes can become task patterns and procedural strategies through a challenge-driven development loop. This gives the system an implicit competence layer that can grow without changing model weights. We formalize system contracts for exact replay and source-version separation, and derive when reuse saves computation. A controlled two-domain implementation tests the exact-replay core on 1,000 synthetic cases. Complete-family holdouts test procedural transfer on 1,000 new-family cases across eight clinical and policy splits, with complete fresh-evidence grounding and perfect invariance to irrelevant-field and insertion-order perturbations. The transfer trace exposes the work required for verified strategy execution. These results establish an initial path toward general intelligence through reusable procedures, typed experience, and developmental transfer.

Problem

• Generalist Agents
• Experience Reuse
• Solution Validity
• Task Adaptation
• Verified Experience

Innovation

• verified experience layer
• meta-controller
• challenge-driven development
• exact replay
• developmental transfer