HyEvo通过混合推理与代码节点，自动生成高效智能工作流。
HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
- 融合概率推理与确定性代码节点，分担大模型计算负担。
- 在多个基准上表现优于现有方法，推理成本降低19倍、延迟降16倍。
- 适合需要高效复杂推理的自动化系统开发者使用。
尽管智能体工作流在解决复杂任务方面展现出巨大潜力，但现有自动化生成方法效率低且性能不足，因其依赖预定义的操作符库和全由大语言模型（LLM）组成的同质化工作流，所有任务级计算均通过概率推理完成。为解决这些问题，我们提出HyEvo，一个自动工作流生成框架，采用异构原子合成策略。HyEvo将概率性LLM节点用于语义推理，同时引入确定性代码节点执行规则化操作，将可预测任务从LLM推理中卸载，显著降低推理开销与执行延迟。为高效探索混合搜索空间，HyEvo采用由LLM驱动的多岛进化策略，并结合反思-生成机制，通过执行反馈迭代优化工作流拓扑与节点逻辑。全面实验表明，HyEvo在多种推理与编码基准上持续优于现有方法，相比最先进的开源基线，推理成本最高降低19倍，执行延迟最高降低16倍。
原文摘要 · Abstract (English)
Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.
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。