Tool-space Interference: An emerging problem for LLM agents
Tool-space interference occurs when adding an otherwise reasonable agent or tool to a team or agent reduces end-to-end task performance. We study the phenomenon in an analysis of 1470 MCP servers and make practical suggestions…
A brain-inspired agentic architecture to improve planning with LLMs
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…
GigaTIME: Scaling tumor microenvironment modeling using virtual population generated by multimodal AI
Using AI-generated virtual populations, Microsoft researchers uncovered hidden cellular patterns that could reshape how we understand and treat cancer.
Member of Technical Staff – Multimodal – MAI Superintelligence Team
Join Microsoft AI in building one of the world’s most advanced foundation models. Our mission is to push the boundaries of scale, performance, and deployment, creating frontier AI systems that power transformative experiences across Microsoft.…
Reinforcement Learning Systems
Microsoft AI is looking for a Member of Technical Staff – Reinforcement Learning Systems to help build the world’s most advanced reinforcement learning systems. We are responsible for designing, developing, and operating the large-scale reinforcement…