Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
This work addresses workflow adherence issues in LLM-based task-oriented dialogue systems for domains like banking, flights, and healthcare, representing an incremental improvement through a novel modular framework.
The paper tackles the problem of LLMs struggling with long, conditional workflows in task-oriented dialogue systems by introducing WARPP, a training-free framework that combines multi-agent orchestration with runtime personalization, resulting in improved workflow adherence, parameter fidelity, and tool accuracy, with reduced token usage compared to baselines.
Large language models (LLMs) are increasingly applied in task-oriented dialogue (TOD) systems but often struggle with long, conditional workflows that involve external tool calls and depend on user-specific information. We present Workflow Adherence via Runtime Parallel Personalization, or WARPP, a training-free, modular framework that combines multi-agent orchestration with runtime personalization to improve workflow adherence in LLM-based systems. By dynamically pruning conditional branches based on user attributes, the framework reduces reasoning overhead and narrows tool selection at runtime. WARPP deploys a parallelized architecture where a dedicated Personalizer agent operates alongside modular, domain-specific agents to dynamically tailor execution paths in real time. The framework is evaluated across five representative user intents of varying complexity within three domains: banking, flights, and healthcare. Our evaluation leverages synthetic datasets and LLM-powered simulated users to test scenarios with conditional dependencies. Our results demonstrate that WARPP outperforms both the non-personalized method and the ReAct baseline, achieving increasingly larger gains in parameter fidelity and tool accuracy as intent complexity grows, while also reducing average token usage, without any additional training.