How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
Year: 2026
Type: conference-paper
Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, etc., which inevitably fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency.We propose ONEMODEL, an applicable paradigm shift from external workflows to internalized knowledge representation.Unlike modular systems that slice fluid user intents into static steps, ONEMODEL consolidates complex business logic and SOPs directly into the model's parameters.Through Continual Pretraining (CPT) and logic-compilation SFT, we transform fragmented business rules into the model's intuitive reasoning within a unified attention space.Deployed in our global financial service system, ONEMODEL effectively breaks the trade-off between latency, accuracy, and complexity.Online A/B testing demonstrates end-to-end latency reduction of more than 50% (18.7s→ 8s) while the Intelligent Resolution Rate (IRR) jumps from 64.3% to 83.3%.The results demonstrate our paradigm ONEMODEL effectively replaces brittle engineering logic with internalized cognitive intuition, offering a scalable and future-proof blueprint for transitioning industrial agents from complex, errorprone workflows to unified model architectures.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166825258