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

• URL: http://arxiv.org/abs/2608.19902v1
• Date: Thu, 20 Aug 2026 11:13:27 GMT
• Title: Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis
• Abstract summary: We present Brain Researcher, an agentic research harness operating in a neuroimaging researcher's computational environment.<n>In benchmarks, Brain Researcher increased first-choice tool-selection accuracy across seven models by 70.2 percentage points.<n>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.
• Score: 59.44063760362954
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• BrainPilot: Automating Brain Discovery with Agentic Research [27.57098883420861]
  We present textbfBrainPilot a textbffully open-source multi-agent system that accelerates brain science research with traceable logs and agent-verified results.<n>A principal investigator (PI) agent coordinates specialist agents grounded in curated domain knowledge.<n>Every major step is recorded in the Graph of Trace, an auditable record that links subgoals, tool use, evidence, and claims.
  arXiv  Detail & Related papers  (2026-07-16T14:49:25Z)
• CausalGame: Benchmarking Causal Thinking of LLM Agents in Games [55.189910630332065]
  CausalGame is a benchmark for evaluating the causal thinking capabilities of AI Scientists.<n>We design 14 scenarios that incorporate selection bias, measurement error, and hidden confounders.<n>The best model reaches only 68.0% survival against analytical optima of 78-85%, and merely 5-7% of sessions receive credits on the causal-reasoning rubrics.
  arXiv  Detail & Related papers  (2026-07-05T13:08:51Z)
• The Agentic Garden of Forking Paths [27.003267976848225]
  We show that AI agents capture much of the analytical variation among human researchers while making these paths explicit.<n>Across four high-stakes domains, assigning different personas is sufficient for AI agents to report divergent, often opposing, conclusions.<n>Despite reaching opposing conclusions, it is difficult to identify clear issues in each analysis based on the final AI reports.
  arXiv  Detail & Related papers  (2026-07-01T22:15:37Z)
• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research [142.29356526274387]
  We present ResearchClawBench, a benchmark for evaluating autonomous scientific research.<n>Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation.
  arXiv  Detail & Related papers  (2026-05-28T16:27:40Z)
• SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning [54.194672921128785]
  We introduce SciResearcher, a fully automated agentic framework for frontier-science data construction.<n>SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence.<n>We develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark.
  arXiv  Detail & Related papers  (2026-05-02T15:26:45Z)
• AI scientists produce results without reasoning scientifically [3.100302590436282]
  Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously.<n>Here, we evaluate LLM-based scientific agents across eight domains, spanning execution to hypothesis-driven inquiry.
  arXiv  Detail & Related papers  (2026-04-20T20:23:42Z)
• Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery [0.17341675932416767]
  This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes.<n>The architecture comprises specialized agents for planning, data analysis, literature search, and novelty detection, unified through a persistent world state.<n> Evaluation on the BixBench computational biology benchmark demonstrated state-of-the-art performance, achieving 48.8% accuracy on open response and 64.4% on multiple-choice evaluation.
  arXiv  Detail & Related papers  (2026-01-18T19:12:41Z)
• AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite [75.58737079136942]
  We present AstaBench, a suite that provides the first holistic measure of agentic ability to perform scientific research.<n>Our suite comes with the first scientific research environment with production-grade search tools.<n>Our evaluation of 57 agents across 22 agent classes reveals several interesting findings.
  arXiv  Detail & Related papers  (2025-10-24T17:10:26Z)
• BLADE: Benchmarking Language Model Agents for Data-Driven Science [21.682416167339635]
  LM-based agents equipped with planning, memory, and code execution capabilities have the potential to support data-driven science.<n>We present BLADE, a benchmark to automatically evaluate agents' multifaceted approaches to open-ended research questions.
  arXiv  Detail & Related papers  (2024-08-19T02:59:35Z)

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.