Uploaded December 2025 | Updated November 2026, 2 hours ago
Inspired by human collective cognition and neuroscience, we conducted two studies showing that a) multi-LLM architectures with mixed communication connectivity lead to better collaborative innovation (Artificial Life 2024), and b) brain-inspired multi-LLM architectures improve multi-step reasoning and planning and substantially reduce hallucination (Nature Communications 2025).
This session aired on December 9, 2025, at Microsoft Research Forum, Season 2 Episode 2.
microsoft.com/en-us/research/video/a-brain-inspired-agentic-architecture-to-improve-planning-with-llms
nature.com/articles/s41467-025-63804-5
Register for the series to learn about future episodes: https://aka.ms/registerresearchforumYTs2e2
Continue watching this episode: https://aka.ms/researchforumYTs2e2
Explore all previous episodes: https://aka.ms/researchforumYTplaylist
Inspired by human collective cognition and neuroscience, we conducted two studies showing that a) multi-LLM architectures with mixed communication connectivity lead to better collaborative innovation (Artificial Life 2024), and b) brain-inspired multi-LLM architectures improve multi-step reasoning and planning and substantially reduce hallucination (Nature Communications 2025).
This session aired on December 9, 2025, at Microsoft Research Forum, Season 2 Episode 2.
microsoft.com/en-us/research/video/a-brain-inspired-agentic-architecture-to-improve-planning-with-llms
nature.com/articles/s41467-025-63804-5
Register for the series to learn about future episodes: https://aka.ms/registerresearchforumYTs2e2
Continue watching this episode: https://aka.ms/researchforumYTs2e2
Explore all previous episodes: https://aka.ms/researchforumYTplaylist










