# NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis

arXiv: https://arxiv.org/abs/2609.01971 · HTML: https://mlsanity.com/paper/2609.01971/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 22 of 22)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [FLAML: A Fast and Lightweight AutoML Library](https://mlsanity.com/paper/1911.04706/) (2019)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects](https://mlsanity.com/paper/2510.21585/) (2025)
- [Neuro-GPT: Towards A Foundation Model for EEG](https://mlsanity.com/paper/2311.03764/) (2023)
- [A Unified, Scalable Framework for Neural Population Decoding](https://mlsanity.com/paper/2310.16046/) (2023)
- [LAMBDA: A Large Model Based Data Agent](https://mlsanity.com/paper/2407.17535/) (2024)
- [Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution](https://mlsanity.com/paper/2407.14668/) (2024)
- [BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals](https://mlsanity.com/paper/2505.18185/) (2025)
- [EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models](https://mlsanity.com/paper/2508.17742/) (2025)
- [EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications](https://mlsanity.com/paper/2512.08959/) (2025)
- [NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines](https://mlsanity.com/paper/2602.13473/) (2026)

## Built on by (most cited first, 1 of 1)

- [AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain--Computer Interfaces](https://mlsanity.com/paper/2609.35456/) (2026)

## Abstract (arXiv)

AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre-trained neural models for physiological data are progressing quickly, their heterogeneous architectures and modality-specific constraints hinder systematic integration, selection, and evaluation. Despite recent advances in large language model (LLM)-based agent systems for intelligent scientific applications, existing approaches often still lack the domain expertise required to effectively select and coordinate diverse neuroscience pre-trained models and handle unique data types in this domain. We present NS-Copilot, an LLM-driven multi-agent system for neuroscience analysis that autonomously supports end-to-end workflows for diverse professional tasks. It unifies domain-specific pre-trained models and supports key neuroscience modalities, including EEG and extracellular spike data, through a natural-language interface. Given raw data and a task description, NS-Copilot orchestrates agents with specialized roles for planning, adaptive control, code generation, and result synthesis, enabling analysis without dataset-specific heuristics. We evaluate NS-Copilot on neuroscience benchmarks spanning Alzheimer's disease, Parkinson's disease, and working memory spike decoding. Across 8 trials per task, the system consistently outperforms strong baselines on the primary metric, demonstrating the ability of NS-Copilot for effective and scalable neuroscience analysis. Our code is publicly available at https://github.com/FrankLiu1102/ns-copilot.