HASHIRU：面向混合智能资源利用的分层代理系统

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization

June 1, 2025

作者: Kunal Pai, Parth Shah, Harshil Patel

cs.AI

摘要

大型语言模型（LLM）的快速发展正推动着自主多智能体系统（MAS）的进步。然而，现有框架往往在灵活性、资源意识、模型多样性和自主工具创建方面存在不足。本文介绍了HASHIRU（混合智能资源利用的层次化智能体系统），这是一种新型MAS框架，旨在提升灵活性、资源效率和适应性。HASHIRU采用“CEO”智能体动态管理专业“员工”智能体，这些智能体根据任务需求和资源限制（成本、内存）实例化。其混合智能优先使用较小、本地的LLM（通过Ollama），同时在必要时灵活调用外部API和更大模型。通过引入包含雇佣/解雇成本的经济模型，促进了团队稳定性和资源高效分配。系统还具备自主API工具创建和记忆功能。在学术论文评审（成功率58%）、安全评估（在JailbreakBench子集上达到100%）、复杂推理（在GSM8K上超越Gemini 2.0 Flash：96%对61%；JEEBench：80%对68.3%；SVAMP：92%对84%）等任务上的评估，展示了HASHIRU的强大能力。案例研究进一步说明了其通过自主成本模型生成、工具集成和预算管理实现自我优化的过程。HASHIRU通过动态层次控制、资源感知的混合智能和自主功能扩展，为构建更健壮、高效和适应性的MAS提供了有前景的解决方案。源代码和基准测试分别发布于https://github.com/HASHIRU-AI/HASHIRU和https://github.com/HASHIRU-AI/HASHIRUBench，现场演示可根据请求在https://hashiruagentx-hashiruai.hf.space获取。

English

Rapid Large Language Model (LLM) advancements are fueling autonomous Multi-Agent System (MAS) development. However, current frameworks often lack flexibility, resource awareness, model diversity, and autonomous tool creation. This paper introduces HASHIRU (Hierarchical Agent System for Hybrid Intelligent Resource Utilization), a novel MAS framework enhancing flexibility, resource efficiency, and adaptability. HASHIRU features a "CEO" agent dynamically managing specialized "employee" agents, instantiated based on task needs and resource constraints (cost, memory). Its hybrid intelligence prioritizes smaller, local LLMs (via Ollama) while flexibly using external APIs and larger models when necessary. An economic model with hiring/firing costs promotes team stability and efficient resource allocation. The system also includes autonomous API tool creation and a memory function. Evaluations on tasks like academic paper review (58% success), safety assessments (100% on a JailbreakBench subset), and complex reasoning (outperforming Gemini 2.0 Flash on GSM8K: 96% vs. 61%; JEEBench: 80% vs. 68.3%; SVAMP: 92% vs. 84%) demonstrate HASHIRU's capabilities. Case studies illustrate its self-improvement via autonomous cost model generation, tool integration, and budget management. HASHIRU offers a promising approach for more robust, efficient, and adaptable MAS through dynamic hierarchical control, resource-aware hybrid intelligence, and autonomous functional extension. Source code and benchmarks are available at https://github.com/HASHIRU-AI/HASHIRU and https://github.com/HASHIRU-AI/HASHIRUBench respectively, and a live demo is available at https://hashiruagentx-hashiruai.hf.space upon request.