infoq.com / .infoq-com-ai-ml-data-eng / Page 4

AWS has introduced Multi-Agent Orchestrator, a framework designed to manage multiple AI agents and handle complex conversational scenarios. The system routes queries to the most suitable agent, maintains context across interactions, and integrates .. ...

Microsoft has announced the release of Magentic-One, a new generalist multi-agent system designed to handle open-ended tasks involving web and file-based environments. This system aims to assist with complex, multi-step tasks across various domains, ...

At QCon SF 2024, Victor Dibia from Microsoft Research explored the complexities of multi-agent systems powered by generative AI. Highlighting common pitfalls like inadequate prompts and poor orchestration, he shared strategies for enhancing ...

Epoch AI in collaboration with over 60 mathematicians from leading institutions worldwide has introduced FrontierMath, a new benchmark designed to evaluate AI systems' capabilities in advanced mathematical reasoning.

Mistral AI recently released Ministral 3B and Ministral 8B, two small language models that are collectively called les Ministraux. The models are designed for local inference applications and outperform other comparably sized models on a range of LLM ...

Explore the dynamic intersection of responsible AI, regulation, and ethics in the FinTech sector. This article highlights key challenges and innovative practices as organizations navigate compliance with evolving guidelines like the EU AI Act. ...

At QCon SF 2024, Ye (Charlotte) Qi of Meta tackled the complexities of scaling large language model (LLM) infrastructure, highlighting the "AI Gold Rush" challenge. She emphasized efficient hardware integration, latency optimization, and production . ...

Architectural Intelligence is the ability to look beyond AI hype and identify real AI components. Determining how, where, and when to use AI elements comes down to traditional trade-off analysis. Like any technology, AI can be used creatively, but .. ...

Jun He gave a talk at QCon SF 2024 titled Efficient Incremental Processing with Netflix Maestro and Apache Iceberg. He showed how Netflix used the system to reduce processing time and cost while improving data freshness.

Chinese researchers fine-tuned Llama-3.2-11B to improve its ability to solve multimodal reasoning problems by going beyond the direct-response or chain-of-thought (coT) approaches to reason step by step in a structured way. Named LLava-CoT, the new . ...