AI
An LLM agent for end-to-end computational materials discovery
Researchers have developed a large language model (LLM) agent system called MAESTRO that can automate the entire process of discovering new materials....
AI
AI
Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
Researchers have developed a testbed to evaluate the behavior of large-language-model (LLM) agents in a social setting. They ran an experiment where L...
AI
Decision Tree and K-Means Analysis of Raman Spectra for Edible Oils: A Physics-Informed AI Approach
Researchers have developed an artificial intelligence approach to identify edible oils using Raman spectroscopy. They used a combination of machine le...
AI
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
A new system called AEGIS aims to prevent malicious agents from abusing resources in large language model (LLM) systems. The Model Context Protocol (M...
AI
Towards Traffic Modelling of Multi-Agent Systems: The Role of Coordination Topology
Researchers have studied the traffic patterns generated by multi-agent systems that use large language models (LLMs). These systems create internal re...
AI
Making Deployments Safe at Meta: Health Checks for Continuous Change-Safety
Meta's Service Health Checker is a system that monitors the health of thousands of services in production. It uses templated metric queries and thresh...
AI
An integrated diffusion-weighted imaging processing and interpretation platform for MR-guided radiotherapy
Researchers have developed a web-based platform that combines raw data from MR-guided radiotherapy with a deep-learning processing pipeline to provide...
AI
Large Scale AI Grading of Handwritten Physics Assessments: Score Agreement and Olympiad Team Selection Outcomes
Researchers have developed an AI system that can grade handwritten physics assessments with high accuracy. The system used a variant of the GPT-5.5 mo...
AI
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
ExploraTwin is an open-access research platform for testing and deploying digital twin simulations. It allows researchers to upload surveys or create ...
AI
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
Researchers have developed a new method for reconstructing MRI images quickly and efficiently. The Consistency Models for Fast MRI Reconstruction Usin...
AI
Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
A new method for diagnosing failures in long-horizon security language models has been proposed. These models struggle to carry information and decisi...
AI
Aggregate, Don't Adapt: Subject-Level Posterior Aggregation and Transductive Calibration for Cross-Site Parkinsonian Gait Severity
Researchers have developed a system that predicts Parkinsonian gait severity from motion recordings taken at clinical sites unseen during training. Th...