Tech Xplore

Flexible position encoding helps LLMs follow complex instructions and shifting states

Most languages use word position and sentence structure to extract meaning. For example, "The cat sat on the box," is not the ...
IEEE

LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Abstract: Future 6G networks require agile medium access control (MAC) protocols for dynamic conditions. Since traditional multi-agent reinforcement learning (MARL) falters with fluctuating agent ...
GitHub

Hetero RL: Heterogeneous Reinforcement Learning

HeteroRL is a novel heterogeneous reinforcement learning framework designed for stable and scalable training of large language models (LLMs) in geographically distributed, resource-heterogeneous ...

Z.ai debuts open source GLM-4.6V, a native tool-calling vision model for multimodal reasoning

Chinese AI startup Zhipu AI aka Z.ai has released its GLM-4.6V series, a new generation of open-source vision-language models ...
Tech Xplore

A smarter way for large language models to think about hard problems

To make large language models (LLMs) more accurate when answering harder questions, researchers can let the model spend more ...
IEEE

LLM-Driven Pareto-Optimal Multi-Mode Reinforcement Learning for Adaptive UAV Navigation in Urban Wind Environments

Abstract: Autonomous drones in complex urban wind environments must balance speed, safety, and energy efficiency under highly variable conditions. Traditional single-policy reinforcement learning ...
TechCrunch

AWS doubles down on custom LLMs with features meant to simplify model creation

Right on the heels of announcing Nova Forge, a service to train custom Nova AI models, Amazon Web Services (AWS) announced more tools for enterprise customers to create their own frontier models. AWS ...
GitHub

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

MARTI is an open-source framework for training LLM-based Multi-Agent Systems (MAS) with Reinforcement Learning (RL). It enables powerful, scalable, and adaptive workflows by combining centralized ...