AI Frontiers
AI Frontiers blog
AutoGen v0.4: Reimagining the foundation of agentic AI for scale, extensibility, and robustness
Gagan Bansal introduces a transformative update to the AutoGen framework that builds on user feedback and redefines modularity, stability, and flexibility to empower the next generation of agentic AI research and applications.
Belief state transformers
John Langford talks about a new transformer architecture that generates compact belief states for goal-conditioned planning, enhancing planning algorithms’ efficiency and effectiveness.
Yadong Lu, Senior Researcher; Thomas Dhome-Casanova, Software Engineer; Jianwei Yang, Principal Researcher; Ahmed Awadallah, Partner Research Manager Graphic User interface (GUI) automation requires agents with the ability to understand and interact with user screens. However, using general purpose LLM models…
By Adam Fourney, Principal Researcher; Gagan Bansal, Senior Researcher; Hussein Mozannar, Senior Researcher; Victor Dibia, Principal Research Software Engineer; Saleema Amershi, Partner Research Manager Contributors: Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang (Eric) Zhu, Friederike Niedtner,…
By Yadong Lu, Senior Researcher; Jianwei Yang, Principal Researcher; Yelong Shen, Principal Research Manager; Ahmed Awadallah, Partner Research Manager Recent advancements in large vision-language models (VLMs), such as GPT-4V and GPT-4o, have demonstrated considerable promise in driving intelligent agent systems…
Direct Nash Optimization: Teaching language models to self-improve with general preferences
This talk discusses teaching language models to self-improve using a preference oracle like GPT-4, framing it as a two-player game to find an optimal policy at a Nash equilibrium, and achieving state-of-the-art win rates against GPT-4 Turbo on benchmarks such…
Adam Fourney discusses the effectiveness of using multiple agents, working together, to complete complex multi-step tasks. He will showcase their capability to outperform previous single-agent solutions on benchmarks like GAIA, utilizing customizable arrangements of agents that collaborate, reason, and utilize…
Besmira Nushi summarizes timely challenges and ongoing work on evaluating and in-depth understanding of large foundation models as well as agent platforms built upon such models at the Microsoft Research Forum.
Dipendra Misra, Senior Researcher at Microsoft Research New York City and AI Frontiers lightning talk presentation at the Microsoft Research Forum.