• Computer Science > Machine Learning [Submitted on 6 Feb 2026] Title:ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces View PDF HTML (experimental)Abstract:We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions • ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes • The system is implemented on top of TEAMLLM, a deterministic execution substrate with immutable artifacts and complete decision traces • We evaluate ACAR on 1,510 tasks spanning four benchmarks: MathArena, Reasoning Gym, LiveCodeBench, and SuperGPQA, using Claude Sonnet 4, GPT-4o, and Gemini 2 • 0 Flash, producing more than 7,550 auditable runs • Results show that sigma-based routing achieves 55

Article Summaries:

  • Computer Science > Machine Learning [Submitted on 6 Feb 2026] Title:ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces View PDF HTML (experimental)Abstract:We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes. The system is implemented on top of TEAMLLM, a deterministic execution substrate with immutabl

Sources: