TL;DR
NeuroClaw is a specialized multi-agent platform designed to facilitate executable, reproducible neuroimaging research across diverse data formats, enhancing transparency and consistency in complex workflows.
Contribution
It introduces NeuroClaw, a comprehensive environment management system with a hierarchical agent architecture and NeuroBench benchmark for neuroimaging research.
Findings
NeuroClaw improves reproducibility and auditability in neuroimaging workflows.
Runs with NeuroClaw yield higher scores across multimodal LLMs.
The platform supports diverse neuroimaging modalities and formats effectively.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
