CORTEX builds verified reusable experience layer for general AI agents
CORTEX: A Verified Experience Layer for Generalist Agents
Artificial IntelligenceMachine LearningMultiagent Systems
Summary
When an AI agent solves a task, it often faces similar tasks later but with different details or rules. Most systems remember text or past talks but don’t know when to reuse old solutions exactly, adapt them, or start fresh. The authors present CORTEX, a framework that carefully records the conditions and results of each task and verifies whether prior solutions still apply. This lets agents reuse or adapt previous experience reliably without retraining, helping them learn and transfer skills over time. The method was tested on many simulated tasks, showing precise reuse and robust transfer across different settings.
What this means in practice
- •For ai system builders: Implement a layer that verifies and reuses past task solutions to improve efficiency and adaptability in AI agents operating in changing environments.
- •For automation engineers: Use verified task experience records to safely adapt or replay automated procedures in clinical or policy systems across different scenarios.
Authors
Garapati Keerthana, Manik Gupta
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.