{"slug": "using-latent-agent-swarms-for-math-discovery-and-optimization-r", "title": "Using latent-agent swarms for math discovery and optimization [R]", "summary": "Google DeepMind's AlphaEvolve, an LLM-driven program-evolution system running on Gemini models, found a faster method for multiplying 4x4 complex matrices, breaking a record that had stood since 1969. The approach has an LLM write a program, score it, and iteratively improve it, and the article notes similar open-source efforts are emerging. The result matters because it shows latent-agent swarms can produce new mathematical discoveries and optimization gains.", "body_md": "Last year Google DeepMind's AlphaEvolve found a faster way to multiply 4x4 complex matrices, beating a record that had stood since 1969. The idea is to let an LLM write a program, score it, and iteratively improve it. So it's called \" evolve \". But AlphaEvolve runs on Gemini models. Similar open-sou", "url": "https://wpnews.pro/news/using-latent-agent-swarms-for-math-discovery-and-optimization-r", "canonical_source": "https://aiflash.com/news/149900/", "published_at": "2026-11-11 17:01:03+00:00", "updated_at": "2026-11-11 17:24:26.792875+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models", "generative-ai"], "entities": ["Google DeepMind", "AlphaEvolve", "Gemini"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/using-latent-agent-swarms-for-math-discovery-and-optimization-r", "markdown": "https://wpnews.pro/news/using-latent-agent-swarms-for-math-discovery-and-optimization-r.md", "text": "https://wpnews.pro/news/using-latent-agent-swarms-for-math-discovery-and-optimization-r.txt", "jsonld": "https://wpnews.pro/news/using-latent-agent-swarms-for-math-discovery-and-optimization-r.jsonld"}}