The paper introduces an agentic-AI framework that autonomously operates an atomic force microscope (AFM) by integrating a large language model with instrument functions via the Model Context Protocol. Three MCP-based agents—AFM Messenger, AFM Pilot, and AFM Doctor—translate natural‑language instructions into commands, assess and adjust image quality, and diagnose artifacts with transparent post‑processing, respectively. Benchmarking shows that the guarded execution layer eliminates wrong‑command execution, and live experiments demonstrate that the AI matches expert operators in image quality and efficiency.
arXiv:2608. 05266v1 Announce Type: new Abstract: Large language model agents are increasingly being developed to control a wide range of scientific characterization tools including microscopes and synchrotron beamlines.
arXiv:2606. 13578v1 Announce Type: cross Abstract: Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach.
OSWorld-Science is a benchmark and evaluation environment for computer-using agents that use visual language models (VLMs) to perform scientific software tasks. It includes 12 VLMs and 146 high-quality tasks across domains such as molecular drawing, pathology image analysis, statistical computing, and physical simulation, with artifact-based evaluation and a harness that logs interactions and supports model comparison. The benchmark was developed through expert proposals and iterative human–AI co‑design, and results show that current VLMs still struggle with key scientific questions, offering insights into factors like language, reasoning, and context length.
La Agente ’Optima is an agentic framework that builds and manages Bayesian optimization campaigns for self‑driving laboratories, separating large language model reasoning from campaign execution. It maintains a persistent optimization state, allowing consistent repetitive loops and auditable decisions, and only returns control to the agent when interpretation or revision is needed. In tests on digital discovery tasks and physical platforms, it corrected measurement failures, improved yields, and recommended formulation changes, outperforming human‑directed campaigns in cost and material usage.
arXiv:2605. 07306v2 Announce Type: replace-cross Abstract: Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains challenging.
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language m...
arXiv:2606. 16802v1 Announce Type: new Abstract: Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment.
LabFactory is a framework that transforms a scientific brief into an executable AI lab, integrating models, knowledge resources, tools, and a controller behind a fixed interface. The builder packages the lab in a metered workspace, and a separate host evaluates the delivered artifact on held‑out inputs, ensuring the system itself is the evaluation target. Across 28 constructions in seven scientific domains, the delivered labs surpassed reference values on all 33 subtests, demonstrating that an AI agent can fully realize a scientific brief into a working, inspectable lab.
The paper investigates whether locally deployed large language models can automate hardware design workflows that involve repetitive, dependency-ordered operations using specialized tools. A Model Context Protocol (MCP) server is created to emulate a proprietary hardware design tool, and a benchmark tests single and multi-step edits, invalid requests, misspelled prompts, and multi-server contexts. Seven open-source models are evaluated across different pipeline choices, revealing that strong models can nearly fully cover expected calls, but reliability hinges on task structure and agent configuration, with comprehensive tool descriptions reducing failures and multi-agent setups aiding weaker models at the cost of extra calls.
MatToolBench is a new benchmark that evaluates multimodal GUI agents on professional materials science software. It contains 204 tasks across 10 tools in three modalities—GUI operation, OriginPro scripting, and code-based database queries—executed inside a Windows 11 VM. The benchmark offers fine-grained, expert-decomposed scoring and a high-performing multimodal judge for aesthetic assessment, revealing that strong general benchmark performance does not transfer to scientific workflows.
arXiv:2606. 18425v1 Announce Type: cross Abstract: Scientific workflow management systems (WMS) support scalable and reproducible execution of complex pipelines, but workflow design, implementation, and debugging remain largely manual and require significant expertise.
arXiv:2603.17043v2 Announce Type: replace Abstract: Physics-aware multimodal large language models (MLLMs) can localize and characterize two-dimensional (2D) material flakes from optical microscopy i...