5 papers · 1 filter
ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling
Xin He, Shunkang Zhang, Kaijie Tang +8
Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many…
Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol
Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer +1
As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate acro…
Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Xin He, Liangliang You, Hongduan Tian +3
Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and e…
LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking
Melvin Wong, Jiao Liu, Thiago Rios +2
This paper presents LLM2TEA, a Large Language Model (LLM) driven MultiTask Evolutionary Algorithm, representing the first agentic AI designer of its kind operating with generative…
Generative AI-based Prompt Evolution Engineering Design Optimization With Vision-Language Model
Melvin Wong, Thiago Rios, Stefan Menzel +1
Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is ofte…