Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis

2026-08-20

AI Summary

为解决AI在科学分析中的选择性分析和过早成功声明等问题，通过Brain Researcher平台规范分析流程，提高工具选择准确性和分析结果的可验证性。

Abstract

AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the evidence supports. Agents may reproduce failures including selective analysis, premature declarations of success and optimization of imperfect criteria. We present Brain Researcher, an agentic research harness operating in a neuroimaging researcher's computational environment under rules for admissible analyses, required checks and claim scope. In benchmarks, Brain Researcher increased first-choice tool-selection accuracy across seven models by 70.2 percentage points (23.3% without it versus 93.6% with it) and verifiable grounding from 4.6% to 22.0%. In collaborator-led and self-evolving studies, multiverse analyses exposed analytic-choice sensitivity, and scientific review classified claims as accepted, qualified, revised, blocked, rejected or deferred. By linking decisions to evidence and provenance, Brain Researcher embeds methodological judgment within the workflow, not after it.

Problem

• AI agents
• scientific analyses
• analytic rigor
• neuroimaging data analysis
• defensible claim

Innovation

• agentic AI
• neuroimaging data analysis
• analytic rigor
• methodological judgment