Scholar
Hussein Mozannar
Google Scholar ID: XCfZyIkAAAAJ
Microsoft Research
Citations & Impact
Citations
1,573
H-index
16
i10-index
18
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- Magentic-UI: A human-centered interface for interacting with AI agents
- Magentic-one: A generalist multi-agent system for solving complex tasks
- Need Help? Designing Proactive AI Assistants for Programming
- [arxiv 2024] - proposes an architecture consisting of a lead orchestrator agent that delegates tasks to other agents to solve complex tasks that require web navigation and code execution
- Challenges in Human-Agent Communication [arxiv 2024] - lists 10 challenges when AI agents start to interact with humans
- Microsoft AutoGen - an open source programming framework for agentic AI
- Reading between the lines: Modeling user behavior and costs in AI-assisted programming [CHI 2024]
- When to show a suggestion? Integrating human feedback in AI-assisted programming [AAAI 2024]
- The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers - proposes a human evaluation method to assess how different AI models (GPT-3.5, CodeLlama,...) improve programmer productivity
- Simulating Iterative Human-AI Interaction in Programming with LLMs - proposes a simulation environment for evaluating AI-assisted programming interfaces
Research Experience
- Currently working at Microsoft Research AI Frontiers, building AI agents (from the model to the interface) that can assist people in tasks requiring web interaction.
Education
- PhD from MIT in Social & Engineering Systems and Statistics (2024); Undergraduate degree in Computer Engineering from the American University of Beirut (2019).
Background
- Senior Researcher at Microsoft Research AI Frontiers, focusing on augmenting humans with AI to help them complete tasks more efficiently. Specifically, he focuses on building AI models and agents that complement human expertise and designing interaction schemes to facilitate human-AI interaction. The main applications of his research have been software development, computer and browser use, and healthcare.
Miscellany
- Can be reached at hmozannar@microsoft.com.
