Gagan Bansal

Gagan Bansal

Principal Researcher, Microsoft Research

Co-creator of AutoGen. I build agentic frameworks, state-of-the-art agent systems, evaluation methods, and tools for the agentic ecosystem. My research also develops theories of human-agent interaction. Currently exploring useful societies of agents. I love building in the open—most of my work ships as open-source and I pair-program with collaborators across research and engineering.

Generative Agents

Open-source frameworks and systems that orchestrate teams of AI agents—from architecture to deployment at Microsoft scale.

AutoGen: Flexible Conversation Patterns

AutoGen

Co-creator

The most widely adopted open-source multi-agent framework—50k+ GitHub stars, powering Microsoft's Agent Framework.

COLM 2024 Best Paper
Magentic-One
Co-lead · Tech Report 2024

Five specialized agents orchestrated to browse, code, and reason—state-of-the-art on GAIA and WebArena.

Magentic Marketplace
Co-lead · Tech Report 2025 · GitHub

What happens when AI agents negotiate on behalf of humans? A simulation platform built with economists to find out.

MarkItDown
Co-lead · 50k+ GitHub stars

Converts PDFs, DOCX, images, and 20+ formats to Markdown. 50k+ stars, 126k downloads/day.

Human-Centered GenAI

Agents fail in ways chatbots don't. I study where human-AI collaboration breaks down and build systems that fix it.

Magentic-UI: Human-centered web agent

Magentic-UI

Co-lead

A web agent that plans with users before acting. Co-planning, guardrails, and full transparency—not autonomy for its own sake.

Tech Report 2025
Challenges in Human-Agent Communication
Tech Report 2025

A taxonomy of 12 breakdowns in human-agent communication—from intent mismatch to transparency overload.

Reading Between the Lines
CHI 2024 · Honorable Mention

The largest observational study of Copilot usage. Main finding: programmers spend more time verifying suggestions than writing code.

Does the Whole Exceed its Parts?
CHI 2021

AI explanations only improve decisions when humans have enough expertise to disagree with the model.

Bio

Gagan Bansal is a Principal Researcher at Microsoft Research AI Frontiers, where he co-created AutoGen, one of the most widely adopted open-source frameworks for multi-agent AI systems and now the foundation of Microsoft's Agent Framework. He has co-led the development of Magentic-One, a generalist multi-agent system achieving state-of-the-art on GAIA and WebArena benchmarks; Magentic-UI, a human-in-the-loop web agent with co-planning and guardrails; and Magentic Marketplace, a collaboration with economists studying agent behavior in two-sided markets. His research spans both building agentic AI systems and studying how humans interact with them—identifying fundamental challenges in human-agent communication and examining how AI explanations, uncertainty displays, and code completion tools affect human decision-making and performance. His work has received a Best Paper award at COLM and an Honorable Mention at CHI. He holds a Ph.D. in Computer Science from the University of Washington, where he was advised by Dan Weld, and a B.Tech from IIT Delhi.