Our research spans agent frameworks, self-improving systems, and AI safety. These papers are the foundation of AG2.
Featured Work
Wu, Bansal, Zhang, et al. · COLM 2024
A framework enabling complex LLM applications through multi-agent conversations. Agents can be customized, composed, and connected to create systems that solve tasks no single model can handle alone.
Read paper
Zhao, Chen, Wu, et al. · arXiv 2025
A reasoning model that improves through self-play without any human-curated training data. The model generates its own curriculum and learns from self-generated feedback.
Read paper
Liu, Wang, Zhang, et al. · arXiv 2025
A comprehensive survey covering agent architectures that adapt and improve through experience: what to evolve, when, and how.
Read paper
11 papers · Last updated January 2026
We work with universities, research labs, and industry partners on multi-agent AI. If you have ideas for benchmarks, experiments, or new research directions, we'd like to hear from you.
Get in touch →