让大模型在复杂任务中更准执行，还能省资源。
Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
- 运行时并行个性化，动态裁剪条件分支以减少推理负担。
- 复杂任务下工具调用准确率提升，比基线高15%以上，且耗能更低。
- 无需训练，适合银行、医疗等需精准流程的对话系统部署。
大型语言模型（LLMs）在面向任务的对话（TOD）系统中应用日益广泛，但在涉及外部工具调用和用户特定信息的长而复杂的条件工作流中常表现不佳。我们提出一种无需训练的模块化框架——运行时并行个性化（WARPP），结合多智能体编排与运行时个性化，提升基于LLM系统的流程遵循能力。通过根据用户属性动态剪枝条件分支，该框架在运行时降低推理开销并缩小工具选择范围。WARPP采用并行架构，由专用个性化代理与领域特定的模块化代理协同工作，实时调整执行路径。我们在银行、航班和医疗三个领域，针对五种不同复杂度的用户意图进行评估，使用合成数据集和由LLM驱动的模拟用户测试存在条件依赖的场景。结果表明，WARPP优于非个性化方法和ReAct基线，在意图复杂度增加时，参数保真度与工具准确性均显著提升，同时平均词元使用量减少，且无需额外训练。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。