Oriel — AI & technology worth noticing, every day.

KORA: Deterministic-First Execution Control for AI Workloads

Paper · https://arxiv.org/abs/2610.35869

arXiv:2610.35869v1 Announce Type: new Abstract: AI applications often invoke a model before they determine whether inference is necessary. That default is useful for ambiguous generative tasks, but it is poorly matched to work that is structured, deterministic, policy-bound, lookup-oriented, or directly verifiable. KORA introduces deterministic-first execution control: a pre-inference control layer that represents requests as task paths, attempts deterministic or structured routes first, validates route outcomes, records telemetry, and escalates to a model-candidate path only when deterministic handling is insufficient. This paper presents KORA as a deterministic-first execution-control architecture and reports bounded evidence from reproducible benchmark and validation workloads. In a reproducible 100-task deterministic-heavy benchmark, KORA-controlled execution avoided 80 of 100 simulated model invocations versus a naive direct baseline, with zero mismatches in the deterministic subset. The workload is intentionally deterministic-heavy: it includes categories such as FAQ lookup, policy/rule checking, schema or format validation, deterministic transformation, and a smaller set of model-needed ambiguous or generative tasks. A separate synthetic customer-support local/no-network validation workload demonstrates route measurement and avoided model-call accounting in an application-shaped setting. These results support bounded model-invocation reduction and validation visibility in documented workloads. They do not establish production behavior, real-provider outcomes, energy outcomes, API-cost reduction, or broad superiority.

First seen by Oriel on .

AI summary

KORA is a deterministic-first execution-control architecture that routes structured tasks without inference when possible, avoiding 80 of 100 simulated model invocations in a bounded benchmark.

  • KORA represents requests as task paths, tries deterministic or structured routes first, validates outcomes, records telemetry, and escalates only when model handling is insufficient.
  • The benchmark covered FAQ lookup, policy checking, schema validation, deterministic transformation, and a smaller set of ambiguous or generative tasks.
  • KORA avoided 80 of 100 simulated model invocations against a naive direct baseline, with zero mismatches in the deterministic subset.
  • A synthetic local customer-support workload demonstrated route measurement and avoided-call accounting in an application-shaped setting.
  • The results do not establish production behavior, real-provider outcomes, energy outcomes, API-cost reduction, or broad superiority.

#ai execution control #deterministic systems #model invocation #benchmarking

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2610.35869v1https://arxiv.org/abs/2610.35869 Read discussion