Alibaba's Metis agent cuts redundant AI tool calls from 98% to 2% — and gets more accurate doing it

Alibaba's HDPO framework trains AI agents to skip unnecessary tool calls, cutting redundant invocations from 98% to 2% while ...
Tech Xplore

Tool can help hunger-relief groups deliver food more efficiently

Engineering researchers at North Carolina State University have developed a mathematical framework that can be used to help ...
IEEE

Trade-off-aware Analog Circuit Sizing Based on A Multitask Surrogate Model-assisted Evolutionary Algorithm

Abstract: Identifying the trade-off relations among various performances is essential in analog integrated circuit sizing, and multiobjective optimization is a routine method. However, mature ...

New AI framework autonomously optimizes training data, architectures and algorithms — outperforming human baselines

EVOLVE, an agentic framework that autonomously optimizes AI training data, model architectures, and learning algorithms — ...
IEEE

Privacy-Preserving Evolutionary Multitasking Optimization: Models and Attacks [Research Frontier]

Abstract: Evolutionary multitasking optimization (EMTO) has emerged as a powerful tool for addressing complex optimization problems, particularly those involving multiple related tasks. However, ...