NeuroClaw Technical Report

• URL: http://arxiv.org/abs/2604.24696v1
• Date: Mon, 27 Apr 2026 16:57:14 GMT
• Title: NeuroClaw Technical Report
• Abstract summary: NeuroClaw is a domain-specialized multi-agent research assistant for neuroimaging research.<n>NeuroClaw operates directly on raw neuroimaging data across formats and modalities.<n>A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills.
• Score: 54.14941057366186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (sMRI, fMRI, dMRI, EEG), long multi-stage pipelines, and persistent reproducibility risks. To address this gap, we present NeuroClaw, a domain-specialized multi-agent research assistant for executable and reproducible neuroimaging research. NeuroClaw operates directly on raw neuroimaging data across formats and modalities, grounding decisions in dataset semantics and BIDS metadata so users need not prepare curated inputs or bespoke model code. The platform combines harness engineering with end-to-end environment management, including pinned Python environments, Docker support, automated installers for common neuroimaging tools, and GPU configuration. In practice, this layer emphasizes checkpointing, post-execution verification, structured audit traces, and controlled runtime setup, making toolchains more transparent while improving reproducibility and auditability. A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills to decompose complex workflows into safe, reusable units. Alongside the NeuroClaw framework, we introduce NeuroBench, a system-level benchmark for executability, artifact validity, and reproducibility readiness. Across multiple multimodal LLMs, NeuroClaw-enabled runs yield consistent and substantial score improvements compared with direct agent invocation. Project homepage: https://cuhk-aim-group.github.io/NeuroClaw/index.html

Related papers

• OpenAI4S: Code as Action, Science as Sessions [57.428071188574]
  We present OpenAI4S, an open-source scientific research agent built around the principle of emphCode as Action, Science as Sessions.<n>OpenAI4S combines a persistent computing runtime with research-session management orchestration is handled through structured tool calls.<n>We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular protein binder design, protein mutation, catalyst screening, and mineral spectroscopy.
  arXiv  Detail & Related papers  (2026-09-14T06:16:59Z)
• NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis [16.317509493719697]
  NSCopilot is a large language model (LLM)-driven multi-agent system for neuroscience analysis.<n>It unifies domain-specific pre-trained models and supports key neuroscience modalities, including EEG and extracellular spike data.<n>It orchestrates agents with specialized roles for planning, adaptive control, code generation, and result.
  arXiv  Detail & Related papers  (2026-09-02T00:57:05Z)
• NeuroPilot: An Agent-Driven Smart Pipeline for Processing, Quality Control, and Managing Neuroimages [12.23473002532912]
  NeuroPilot is a multi-agent system that digitalizes the expertise of neuroimage processing, QC, and data management into three LLM-invocable skills.<n>We deployed NeuroPilot across 17 cohorts spanning infant to aging populations and multiple MRI modalities.<n>The infant processing pipeline achieved a 100% (201/201) completion rate on QC-validated inputs.
  arXiv  Detail & Related papers  (2026-07-30T19:36:53Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research [4.995664191055236]
  NeuroAgent is an agentic framework that automates key preprocessing and analysis steps for neuroimaging data.<n>It supports interactive downstream analysis through natural-language queries.<n>It can reduce the manual effort required for preprocessing and enable end-to-end automated analysis pipelines.
  arXiv  Detail & Related papers  (2026-05-07T17:13:48Z)
• NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration [7.824386969078225]
  NeuroMesh is a multi-domain, cross-platform, and modular decentralized neural inference framework.<n>It standardizes observation encoding, message passing, aggregation, and task decoding in a unified pipeline.<n>We validate NeuroMesh on a heterogeneous team of aerial and ground robots, demonstrating robust operation across diverse task structures and payload sizes.
  arXiv  Detail & Related papers  (2026-04-16T18:54:34Z)
• Cedalion Tutorial: A Python-based framework for comprehensive analysis of multimodal fNIRS & DOT from the lab to the everyday world [0.0]
  Cedalion is a Python-based framework designed to unify model-based and data-driven analysis of fNIRS and DOT data.<n>It supports SNIRF and BIDS standards, supports cloud-executable Jupyter notebooks, and provides containerized analysis pipelines.<n>It implements validated algorithms for signal-quality assessment, motion correction, GLM modelling, and reconstruction, complemented by modules for simulation, data augmentation, and multimodal physiology analysis.
  arXiv  Detail & Related papers  (2026-01-09T16:37:48Z)
• NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models [66.91449452840318]
  We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer.<n>Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training.<n>Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks.
  arXiv  Detail & Related papers  (2025-10-15T01:26:52Z)
• Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli [13.536940903353768]
  High-resolution neural datasets enable foundation models for the next generation of brain-computer interfaces and neurological treatments.<n>Neuroprobe is a suite of decoding tasks for studying multi-modal language processing in the brain.<n>Neuroprobe is built on the BrainTreebank dataset, which consists of 40 hours of iEEG recordings from 10 human subjects performing a naturalistic movie viewing task.
  arXiv  Detail & Related papers  (2025-09-25T22:38:53Z)
• SciML Agents: Write the Solver, Not the Solution [69.5021018644143]
  We introduce two new datasets: a diagnostic dataset of adversarial "misleading" problems; and a large-scale benchmark of 1,000 diverse ODE tasks.<n>We evaluate open- and closed-source LLM models along two axes: (i) unguided versus guided prompting with domain-specific knowledge; and (ii) off-the-shelf versus fine-tuned variants.<n>Preliminary results indicate that careful prompting and fine-tuning can yield a specialized LLM agent capable of reliably solving simple ODE problems.
  arXiv  Detail & Related papers  (2025-09-12T02:53:57Z)
• Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing [4.066607775161713]
  Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention. Here, we establish a common reference frame for computations in digital neuromorphic systems. We demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms.
  arXiv  Detail & Related papers  (2023-11-24T18:15:59Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.