Connecting Large Language Model Agent to High Performance Computing Resource
This work addresses the need for scalable computing in scientific research using LLM agents, but it is incremental as it adapts existing tools rather than introducing a new paradigm.
The authors tackled the problem of enabling large language model agents to access high-performance computing resources for scientific tasks by integrating Parsl into LangChain/LangGraph tool calls, resulting in successful concurrent execution of molecular dynamics simulations on both local workstations and HPC environments like Polaris/ALCF.
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.