arXiv AI September 4, 2026 By Yishu Wang, Wei Liu, Yifan Li, Shengxiang Xu, Xujie Yuan, Ran Li, Yuyu Luo, Jia Zhu, Shimin Di, Min-Ling Zhang, Guixiang Li

PeroMAS: A Multi-agent System of Perovskite Material Discovery

Read the original on arXiv AI →

PeroMAS is a multi-agent system designed for discovering perovskite materials, integrating tools encapsulated as Model Context Protocols to handle the full workflow from literature retrieval to synthesis. It enables design under multi-objective constraints and outperforms single LLM or traditional search methods in discovery efficiency. The system’s effectiveness was validated by real synthesis experiments guided by expert evaluation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 17

Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors

arXiv:2410. 08562v5 Announce Type: replace-cross Abstract: Advanced crystal design can accelerate materials discovery across applications from photovoltaics to spintronics.

By Akihiro Fujii, Yoshitaka Ushiku, Koji Shimizu, Anh Khoa Augustin Lu, Satoshi Watanabe

arXiv AI

Jul 14

AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking

arXiv:2607. 11526v1 Announce Type: cross Abstract: Material property prediction (MPP) infers key properties from chemical composition and structure, accelerating the discovery and optimization of novel materials.

By Hongxiao Li, Wanling Gao

benchmarks

arXiv AI

Jun 6

AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations

arXiv:2605. 26179v2 Announce Type: replace-cross Abstract: Density functional theory (DFT) serves as the basis for computational discovery in materials science and chemistry, yet each calculation demands extensive human effort: adjusting algorithms when convergence stalls, revising plans when unexpected physics emerges, and inserting steps as intermediate results reshape the problem.

By Penghui Yang, Zhonghan Zhang, Yue Li, Xinrun Wang, Yanchen Deng, Yuhao Lu, Bijun Tang, Zheng Liu, Bo An

llms agents benchmarks

arXiv AI

Aug 18

ALKEMIE Agent: an autonomous platform for computational materials design

arXiv:2608. 15776v1 Announce Type: cross Abstract: Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computation workflows remain fragmented and heavily manual, requiring researchers to constantly bridge software tools, data analysis, and intermediate decisions.

By Hongfu Huang, Yuzhe Li, Ao Xu, Bo Liu, Changrui Wang, Kan Tang, Ning Yang, Shengxian Liu, Hanyu Liu, Pengpeng Zhang, Linggang Zhu, Fengkai Liu, Yichen Lu, Tong Zhao, Naihua Miao, Jian Zhou, Zhimei Sun

rag agents efficiency

arXiv AI

Aug 14

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

arXiv:2605. 08756v2 Announce Type: replace Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs).

By Haoze Lv, Ning Lu, Ziang Zhou, Yew-Soon Ong, Shengcai Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 1

Evaluating LLM-based AI agents integrated with materials synthesis tools: the case of atomic layer deposition

The article reviews methods for assessing large language model (LLM) based AI agents in materials synthesis, focusing on their integration with experimental tools. It outlines evaluation strategies—including knowledge, reasoning, tool‑use, and closed‑loop benchmarks—and applies them to atomic layer deposition (ALD) as a case study. A practical framework for evaluating LLMs in this context is also presented.

By Angel Yanguas-Gil

llms agents benchmarks

One email a morning, machine-written

Related stories

Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors

AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking

AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations

ALKEMIE Agent: an autonomous platform for computational materials design

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

Evaluating LLM-based AI agents integrated with materials synthesis tools: the case of atomic layer deposition