The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

This paper compares two agentic AI systems, Claude Code and Codex, on a gravitational wave data analysis pipeline, finding that while both achieve scientific convergence, they exhibit vastly different…

MOSAIC introduces a structured agentic framework that treats automated data science as a staged, context-grounded model selection problem, improving performance and traceability over traditional AutoM…

The paper introduces Compass, an expert-guided LLM agent framework that successfully extracts and integrates thousands of previously inaccessible marine lead records from vast corpora of scientific pa…

This case study demonstrates that in complex scientific software development, human domain expertise and careful supervision are more critical to ensuring the trustworthiness of AI-generated code than…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

The paper evaluates various LLM-based agentic schemes for authoring complex, interactive, multiview genomics visualizations, finding that agentic iteration significantly improves visualization quality…

This paper presents EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.

The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

The BEAMS initiative establishes comprehensive benchmarks and evaluates AI tools for modeling and simulation, finding that current AI tools excel at qualitative discussion tasks but struggle with comp…

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

This paper introduces ATLAS, an active learning framework for discovering interpretable behavioral models in cognitive science.

The paper introduces Crafter, a multi-agent harness that significantly improves the generation of editable, publication-quality scientific figures from diverse inputs, addressing the limitations of ex…

The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechani…

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in spe…

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

The paper introduces extsc{Ptah}, a multi-agent harness designed to improve verifiable multimodal deep research by orchestrating the entire report generation process, ensuring factual grounding and v…

AutoScientists introduces a decentralized, self-organizing team of AI agents that significantly improves long-running scientific experimentation by enabling parallel exploration and knowledge sharing.

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…