# ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations

arXiv: https://arxiv.org/abs/2609.32868 · HTML: https://mlsanity.com/paper/2609.32868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Forecasting Global Weather with Graph Neural Networks](https://mlsanity.com/paper/2202.07575/) (2022)
- [Parsl: Pervasive Parallel Programming in Python](https://mlsanity.com/paper/1905.02158/) (2019)
- [Empowering Scientific Workflows with Federated Agents](https://mlsanity.com/paper/2505.05428/) (2025)
- [Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows](https://mlsanity.com/paper/2505.04997/) (2025)
- [Chat AI: A Seamless Slurm-Native Solution for HPC-Based Services](https://mlsanity.com/paper/2407.00110/) (2024)
- [EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design](https://mlsanity.com/paper/2605.19743/) (2026)
- [Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing](https://mlsanity.com/paper/2607.18485/) (2026)
- [FirecREST: RESTful API on Cray XC systems](https://mlsanity.com/paper/1911.13160/) (2019)
- [VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs](https://mlsanity.com/paper/2510.00031/) (2025)
- [Descriptive Execution of HPC Applications and Workflows](https://mlsanity.com/paper/2607.10081/) (2026)
- [Hierarchical Server Architecture for Agentic Science](https://mlsanity.com/paper/2608.05332/) (2026)

## Abstract (arXiv)

Traditional scientific computing requires researchers to translate intent into environment configuration, resource requests, and executable jobs, then diagnose failures from scheduler and application logs. We present ASCEND (Autonomous Scientific Computing Engine and Novel Discovery), an AI-powered agent system, operated through a command-line or a local web chat interface, that runs the agent on the researcher's own laptop, reaching Slurm clusters and a GPU workstation over multiplexed authenticated SSH, with site-specific execution policies checked by locally executed tools. The language-model agent (Claude Code or Codex, chosen at each launch) is hosted remotely and holds no credentials; an account on each resource suffices, and a public installer links additional clusters or workstations. We report four recorded cases: (1) the agent closed a failure-recovery loop on a planted tensor-device fault, submitting, diagnosing, repairing, and resubmitting it; (2) it reproduced the published evaluation of a weather-forecasting model, recovering an incompletely stated evaluation protocol and agreeing with the published curves to 2.1% (z500) and 2.4% (t850), while identifying two discrepancies in the paper's released materials; (3) it parallelized a released 12,693-line geophysical solver under a requirement of bit-for-bit identity of exported outputs, reducing runtime from about twelve hours to about two; (4) that requirement exposed two instances of undefined behavior in the published solver, both repaired and reported upstream. These cases used ordinary scheduler commands; a separate, pre-specified evaluation of the optional policy validator rejected 29 of 30 constructed violations, held one for approval, and denied 3 of 14 legitimate requests. Autonomy was exercised under author supervision, and agent transcripts were not retained, so intervention rates are not independently verifiable.