01
LLM Agents Overview
Yann Dubois, OpenAI
Completed
Cohort 2
The second cohort drew from the Agentic AI MOOC Fall 2025. Starting with this cohort, Leonardo Gonzalez joined as program head.
- Period
- September to December 2025
- Commitment
- LLM agents, evaluation, and competition
- Focus
- Fall 2025, Agentic AI
Work focus
- Agent foundations and infrastructure.
- Agent evaluation and traceability.
- Applications in code, science, web, and robotics.
Activities
- Weekly readings from the Agentic AI MOOC.
- Implementation and evaluation exercises.
- Competitive project for AgentX AgentBeats.
- Demo and presentation preparation.
Achievements and outcomes
- Team participation in UC Berkeley's AgentX AgentBeats.
- One team placed third worldwide in the Gaming category, presented at AI Tinkerers, and received a full scholarship to the Hardcore AI program.
Video archive
Cohort resources
03
Post-Training Verifiable Agents
Jiantao Jiao, NVIDIA
04
07
Predictable Noise in LLM
Sida Wang, Meta
08
AI Agents to Automate Scientific Discoveries
James Zou, Stanford
09
Practical Lessons from Deploying Real-World AI Agents
Clay Bavor, Sierra
11
Autonomous Agents: Embodiment, Interaction, and Learning
Peter Stone, UT Austin / Sony AI