HiVA让智能体自动构建可演化的工作流图，提升复杂任务执行效率。
HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
- 用语义拓扑演化算法自组织生成可动态调整的智能体工作流图
- 在对话、编程等任务中提升5-10%准确率，资源效率更优
- 适合需要长期自主决策与结构优化的AI系统开发者
自主智能体在推动通用人工智能发展中至关重要，能通过大语言模型（LLMs）实现问题分解与工具编排。然而现有范式存在关键权衡：可复用的固定流程在环境变化时需手动重配；灵活的反应式循环无法提炼可迁移的推理结构。我们提出分层可变智能体（HiVA），将智能体工作流建模为自组织图谱，采用语义拓扑演化（STEV）算法，在混合语义-拓扑空间中利用文本梯度作为离散域代理实现反向传播优化。迭代过程包含引入多臂赌博机的前向路由、基于环境反馈的诊断梯度生成，以及协同更新个体语义与拓扑结构，实现未知环境中的集体优化。在对话、编码、长上下文问答、数学推理及智能体基准测试中，任务准确率提升5-10%，资源效率优于现有基线，验证了HiVA在自主任务执行中的有效性。
原文摘要 · Abstract (English)
Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one hand, reusable fixed workflows require manual reconfiguration upon environmental changes; on the other hand, flexible reactive loops fail to distill reasoning progress into transferable structures. We introduce Hierarchical Variable Agent (HiVA), a novel framework modeling agentic workflows as self-organized graphs with the Semantic-Topological Evolution (STEV) algorithm, which optimizes hybrid semantic-topological spaces using textual gradients as discrete-domain surrogates for backpropagation. The iterative process comprises Multi-Armed Bandit-infused forward routing, diagnostic gradient generation from environmental feedback, and coordinated updates that co-evolve individual semantics and topology for collective optimization in unknown environments. Experiments on dialogue, coding, Long-context Q&A, mathematical, and agentic benchmarks demonstrate improvements of 5-10% in task accuracy and enhanced resource efficiency over existing baselines, establishing HiVA's effectiveness in autonomous task execution.
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。