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

arXiv: https://arxiv.org/abs/2608.19902 · HTML: https://mlsanity.com/paper/2608.19902/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 154 references that are in the map.
- First posted on arXiv 20 Aug 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, 7 of 7)

- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [A foundation model of vision, audition, and language for in-silico neuroscience](https://mlsanity.com/paper/2605.04326/) (2026)
- [Agentic Uncertainty Reveals Agentic Overconfidence](https://mlsanity.com/paper/2602.06948/) (2026)
- [NeuroClaw Technical Report](https://mlsanity.com/paper/2604.24696/) (2026)
- [What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants](https://mlsanity.com/paper/2605.30777/) (2026)

## Abstract (arXiv)

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.