让大模型代理直接调用高性能计算资源，加速科学计算任务。
Connecting Large Language Model Agent to High Performance Computing Resource
- 用ParSl将大模型工具调用接入高性能计算环境，实现并行执行。
- 在本地工作站和Polaris超算上验证，任务并发执行效率提升显著。
- 适合需要大规模模拟的科研人员，如分子动力学研究者。
大语言模型代理工作流使LLM能够调用工具函数以提升特定科学领域问题的处理能力。为应对大规模科学研究需求，需接入计算资源与并行计算环境。本文将ParSL集成至LangChain/LangGraph工具调用框架中，弥合大模型代理与计算资源之间的鸿沟。实现了两种工具调用方案，并在本地工作站及Polaris/ALCF超算环境上进行测试。第一种方案通过ParSL-enabled LangChain工具节点，将函数任务并行排队至ParSL工作者执行；第二种方案将工具函数转换为ParSL集合函数，更适合超算环境中的大规模任务。实验中，大模型代理被提示运行分子动力学模拟，针对不同蛋白结构与模拟条件。结果表明，所有工具任务均由ParSL在可用计算资源上高效并发管理与执行。
原文摘要 · Abstract (English)
The Large Language Model agent workflow enables the LLM to invoke tool functions to increase the performance on specific scientific domain questions. To tackle large scale of scientific research, it requires access to computing resource and parallel computing setup. In this work, we implemented Parsl to the LangChain/LangGraph tool call setup, to bridge the gap between the LLM agent to the computing resource. Two tool call implementations were set up and tested on both local workstation and HPC environment on Polaris/ALCF. The first implementation with Parsl-enabled LangChain tool node queues the tool functions concurrently to the Parsl workers for parallel execution. The second configuration is implemented by converting the tool functions into Parsl ensemble functions, and is more suitable for large task on super computer environment. The LLM agent workflow was prompted to run molecular dynamics simulations, with different protein structure and simulation conditions. These results showed the LLM agent tools were managed and executed concurrently by Parsl on the available computing resource.
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。