CAPE: Capability Achievement via Policy Execution
This addresses the deployment reliability issue for AI developers and users by providing a systematic method to enforce requirements, though it builds on existing concepts like verification and training loops.
The paper tackles the problem of AI systems failing to reliably satisfy explicit, context-dependent constraints despite strong benchmark performance, introducing Capability Engineering and the CAPE protocol to reduce violation rates by 81% relative to DPO across 109,500 examples in six domains.
Modern AI systems lack a way to express and enforce requirements. Pre-training produces intelligence, and post-training optimizes preferences, but neither guarantees that models reliably satisfy explicit, context-dependent constraints. This missing abstraction explains why highly intelligent models routinely fail in deployment despite strong benchmark performance. We introduce Capability Engineering, the systematic practice of converting requirements into executable specifications and training models to satisfy them by default. We operationalize this practice through CAPE (Capability Achievement via Policy Execution), a protocol implementing a Specify -> Verify -> Correct -> Train loop. CAPE is grounded in two empirical findings: (1) contextual objectivity, where properties appearing subjective become objective once context is fixed (inter-annotator agreement rises from kappa = 0.42 to kappa = 0.98), and (2) verification-fidelity scaling, where verification accuracy improves with model scale (r = 0.94), unlike preference agreement which plateaus at 30 to 50 percent disagreement regardless of compute. Across 109,500 examples in six domains, CAPE reduces violation rates by 81 percent relative to DPO (standard deviation less than 0.3 percent). By replacing per-example annotation with reusable specifications, CAPE reduces costs by 5 to 20 times and shortens timelines from months to weeks. We release the CAPE protocol, PredicateGraph schema, CPL specification language, and policy packs under Apache 2.0. We also launch CapabilityBench, a public registry of model evaluations against community-contributed policies, shifting evaluation from intelligence benchmarks toward capability measurement.