AI Agent Frontier

1.43K subscribers

42 videos

Agentic AI Research, see Homepages: https://agentic-ai-frontier-seminar.github.io/ https://sites.google.com/view/saferl-seminar/home https://saferl.online/2022/

Latest Videos

Prof. Leslie Kaelbling RL Rational Learning

Prof. Sergey Levine Robotic Foundation Models

Dr. Sida Wang Measuring all the noises of agentic LLM Evals

Prof. Graham Neubig Lessons from the Trenches in Building Agents for Software Development

Prof. Lifu Huang Goodhart’s Revenge Reward Hacking in RL-Tuned LLMs, and How We Fight Back

Prof. Pulkit Agrawal Rethinking Post Training

Prof. Daniel Fried Inducing and Using Abstractions of Agent Actions

Professor Maarten Sap Enabling Human-centric and Culturally Aware Safety of AI Agents

Prof. Yu Su Computer Use Modern Moravec’s Paradox

Prof. Melanie Mitchell Investigating Abstract Reasoning in Humans and Machines

Prof. Diyi Yang Automation or Augmentation Optimizing Human-AI Collaboration

Prof. Muhao Chen Reasoning Guardrails for the Agentic Web

Prof. Huan Sun Advancing the Capability and Safety of Computer-Use Agents Together

Prof. Lin Yang Winning Gold at IMO 2025 with a Model-Agnostic Self-Verification Pipeline

Prof. Eric Xin Wang Building AI Agents that Reason and Act Like Humans

Prof. Natasha Jaques Multi-agent Reinforcement Learning (MARL) for LLMs

Prof. Peter Stone Human-in-the-Loop Machine Learning for Robot Navigation and Manipulation

Prof. Alane Suhr Training Language-Based Agents

Prof. Manling Li RAGEN Training Agents by Reinforcing Reasoning

Prof. Furong Huang Towards AI Security – An Interplay of Stress-Testing and Alignment

Dr. Akshara Rai Sim2Real Learning for Home Robots

Prof. Tengyu Ma STP Self-play LLM Theorem Provers with Iterative Conjecturing and Proving

Representation-based Reinforcement Learning

Contextual Bandits with Constraints Revisited A Modular Approach with Improved Rates

The future of large embodied model

HAPPO

MACPO

The Curious Price of Distributional Robustness in Reinforcement Learning

Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning

Explainable reinforcement learning approaches for safe and interpretable autonomous driving