Artificial-intelligence

This post explores the X-MAS framework, which investigates the benefits of using diverse Large Language Models (LLMs) within multi-agent systems (MAS). It details X-MAS-Bench, a comprehensive testbed evaluating 27 LLMs across 5 domains and 5 MAS functions, revealing that no single LLM excels universally. Building on these findings, the paper demonstrates significant performance improvements (up to 47-63% on challenging math problems) when transitioning homogeneous MAS to heterogeneous configurations, highlighting the potential of leveraging collective intelligence from diverse LLMs.

Google I/O '25 unleashed a torrent of AI innovation. Dive into the enhanced Gemini 2.5 Pro, the immersive Google Beam video platform, the creative Lyria RealTime music AI, the powerful TPU Ironwood, and groundbreaking updates to Meet and Search.

Explore the history and technical approaches in the quest for Artificial General Intelligence, from early symbolic AI and expert systems to deep learning and probabilistic programming, illustrated by real-world applications like nuclear monitoring.

Explore the latest developments in Manus AI, China's groundbreaking autonomous AI agent that promises to revolutionize tasks from web development to financial analysis. Discover its capabilities, limitations, and how it stacks up against competitors like OpenAI's Deep Research.

DeepSeek is accelerating the release of its R2 model, promising groundbreaking advancements in AI reasoning, coding, and multilingual capabilities. With a focus on cost efficiency and open-source innovation, R2 could challenge Western AI giants like OpenAI and Anthropic.