ExACT combines Reflective-MCTS and Exploratory Learning to improve AI agents' decision-making, enabling test-time compute scaling. Learn how these methods help agents refine strategies for state-of-the-art performance and improved computational efficiency. The post ExACT: Improving AI agents’ decision-making via test-time compute scaling appeared first on Microsoft Research.

Advances in low-bit quantization techniques enable efficient operation of LLMs on resource-constrained edge devices. Discover how innovations like T-MAC, Ladder, and LUT Tensor Core improve computational efficiency and enhance hardware compatibility. The post Advances to low-bit quantization enable LLMs on edge devices appeared first on Microsoft Research.

In this issue: A new approach to multimodal pretraining for remote sensing; Managed-retention memory for the AI era; Improving detection of macular telangiectasia type 2; Generalizing symbolic automata. The post Research Focus: Week of January 27, 2025 appeared first on Microsoft Research.

In this edition: Privacy enhancements for multiparty deep learning; using smaller, open-source models to provide relevance judgments; new tool uses AI, data to automate innovation and development; Yasuyuki Matsushita named IEEE 2025 Computer Society Fellow. The post Research Focus: Week of January 13, 2025 appeared first on Microsoft Research.

Microsoft researchers introduce MatterGen, a model that can discover new materials tailored to specific needs—like efficient solar cells or CO2 recycling—advancing progress beyond trial-and-error experiments. The post MatterGen: A new paradigm of materials design with generative AI appeared first on Microsoft Research.

Announcing AutoGen 0.4, fully reimagined library for building advanced agentic AI systems, developed to improve code quality and robustness. Its asynchronous, event-driven architecture is designed to support dynamic, scalable workflows. The post AutoGen v0.4: Reimagining the foundation of agentic AI for scale, extensibility, and robustness appeared first on Microsoft Research.

AIOpsLab is an open-source framework designed to evaluate and improve AI agents for cloud operations, offering standardized, scalable benchmarks for real-world testing, enhancing cloud system reliability. The post AIOpsLab: Building AI agents for autonomous clouds appeared first on Microsoft Research.

NeoMem: hardware/software co-design for CXL-native memory tiering; Chimera: accurate retrosynthesis prediction by ensembling models with diverse inductive biases; GA4GH task execution API enables multicloud task execution. The post Research Focus: Week of December 16, 2024 appeared first on Microsoft Research.

PromptWizard from Microsoft Research is now open source. It is designed to automate and simplify AI prompt optimization, combining iterative LLM feedback with efficient exploration and refinement techniques to create highly effective prompts in minutes. The post PromptWizard: The future of prompt optimization through feedback-driven self-evolving prompts appeared first on Microsoft Research.

GraphRAG helps advance AI use in complex domains like science. Thanks to enthusiastic adoption and community engagement, we’ve upgraded the pre-release version. Check out the major ergonomic and structural updates in GraphRAG 1.0. The post Moving to GraphRAG 1.0 – Streamlining ergonomics for developers and users appeared first on Microsoft Research.