BenchmarkQED is an open-source toolkit for benchmarking RAG systems using automated query generation, evaluation, and dataset prep. It shows that LazyGraphRAG outperforms standard methods, especially on complex, global queries.
The recent advances in quantum computing offer many advantages—but also challenge current cryptographic strategies. Learn how FrodoKEM could help strengthen security, even in a future with powerful quantum computers.
Magentic-UI, new from Microsoft Research, is an open-source research prototype of a human-centered AI agent, designed to work with people to complete complex, web-based tasks in real time over a web browser.
ADeLe, a new evaluation method, explains what AI systems are good at—and where they’re likely to fail. By breaking tasks into ability-based requirements, it has the potential to provide a clearer way to evaluate and predict AI model performance.
In this issue: New research on compound AI systems and causal verification of the Confidential Consortium Framework; release of Phi-4-reasoning; enriching tabular data with semantic structure, and more.
The first Microsoft Research Fusion Summit brought together global experts to explore how AI can help unlock the potential of fusion energy. Discover how collaborations with leading institutions can help speed progress toward clean, scalable energy.
Learn about a new white paper on Societal AI, an interdisciplinary framework for guiding AI development that reflects shared human values. It presents key research challenges and emphasizes collaboration across disciplines.
In this issue: our CHI 2025 & ICLR 2025 contributions, plus research on causal reasoning & LLMs; countering LLM jailbreak attacks; and how people use AI vs. AI-alone. Also, SVP of Microsoft Health Jim Weinstein talks rural healthcare innovation.
Join us at CHI 2025 to explore how AI systems can be used as Tools for Thought as we reimage AI’s role in human thinking. Learn about new research, prototypes, and a workshop on designing AI that supports critical thinking, decision-making, and creativity.
Semantic Telemetry Project data show that people who use AI for more professional and complex tasks are more likely to keep using the tool and to use it more often. Novice AI users engage in simpler tasks, but their usage is becoming more complex.
Developers spend a lot of time debugging code. Learn how debug-gym can equip AI agents to help, enabling them to set breakpoints, navigate the codebase, and print runtime variable values on demand, so they better understand the code and its execution flow.
In this issue: We introduce a new dataset designed to assist renewable energy infrastructure planners, a new method for denoising MRI imagery, and an AI tool for analyzing distant galaxies. Check out our latest research and other updates.
Meet our community of researchers, learn about exciting research topics, and grow your network
Ongoing conversations at the cutting edge of research
Join us for a continuous exchange of ideas about research in the era of general AI