AI Agent Frontier

@UCo_QY2SB3-ZUdyAWJRHSdcg - 734 subscribers

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

Home Videos Live Playlists

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

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

46 views - 1 week ago

Prof. Pulkit Agrawal: Rethinking Post Training

Prof. Pulkit Agrawal: Rethinking Post Training AI Agent Frontier

69 views - 1 week ago

Prof. Daniel Fried: Inducing and Using Abstractions of Agent Actions

Prof. Daniel Fried: Inducing and Using Abstractions of Agent Actions AI Agent Frontier

114 views - 2 weeks ago

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

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

78 views - 3 weeks ago

Prof. Yu Su: Computer Use: Modern Moravec’s Paradox

Prof. Yu Su: Computer Use: Modern Moravec’s Paradox AI Agent Frontier

134 views - 4 weeks ago

Prof. Melanie Mitchell: Investigating Abstract Reasoning in Humans and Machines

Prof. Melanie Mitchell: Investigating Abstract Reasoning in Humans and Machines AI Agent Frontier

140 views - 4 weeks ago

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

Prof. Diyi Yang: Automation or Augmentation? Optimizing Human-AI Collaboration AI Agent Frontier

280 views - 3 months ago

Prof. Muhao Chen: Reasoning Guardrails for the Agentic Web

Prof. Muhao Chen: Reasoning Guardrails for the Agentic Web AI Agent Frontier

131 views - 3 months ago

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

Prof. Huan Sun: Advancing the Capability and Safety of Computer-Use Agents Together AI Agent Frontier

124 views - 3 months ago

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

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

261 views - 4 months ago

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

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

421 views - 4 months ago

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

Prof. Natasha Jaques: Multi-agent Reinforcement Learning (MARL) for LLMs AI Agent Frontier

1K views - 4 months ago

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

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

382 views - 4 months ago

Prof. Alane Suhr: Training Language-Based Agents

Prof. Alane Suhr: Training Language-Based Agents AI Agent Frontier

127 views - 5 months ago

Prof. Manling Li: RAGEN: Training Agents by Reinforcing Reasoning

Prof. Manling Li: RAGEN: Training Agents by Reinforcing Reasoning AI Agent Frontier

560 views - 5 months ago

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

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

158 views - 6 months ago

Dr. Akshara Rai: Sim2Real Learning for Home Robots

Dr. Akshara Rai: Sim2Real Learning for Home Robots AI Agent Frontier

284 views - 7 months ago

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

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

262 views - 7 months ago

Representation-based Reinforcement Learning

Representation-based Reinforcement Learning AI Agent Frontier

419 views - 1 year ago

Contextual Bandits with Constraints Revisited: A Modular Approach with Improved Rates

Contextual Bandits with Constraints Revisited: A Modular Approach with Improved Rates AI Agent Frontier

155 views - 1 year ago

The future of large embodied model

The future of large embodied model AI Agent Frontier

377 views - 1 year ago

HAPPO AI Agent Frontier

75 views - 1 year ago

MACPO AI Agent Frontier

151 views - 1 year ago

The Curious Price of Distributional Robustness in Reinforcement Learning:

The Curious Price of Distributional Robustness in Reinforcement Learning: AI Agent Frontier

610 views - 2 years ago

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

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

177 views - 2 years ago

Explainable reinforcement learning approaches for safe and interpretable autonomous driving

Explainable reinforcement learning approaches for safe and interpretable autonomous driving AI Agent Frontier

893 views - 2 years ago

Towards robust, efficient, and safe reinforcement learning

Towards robust, efficient, and safe reinforcement learning AI Agent Frontier

747 views - 2 years ago

Safe Reinforcement Learning in the Presence of Non-stationarity: Theory and Algorithms

Safe Reinforcement Learning in the Presence of Non-stationarity: Theory and Algorithms AI Agent Frontier

691 views - 2 years ago

Safe and Reliable Robot Reinforcement Learning in Dynamic Environments

Safe and Reliable Robot Reinforcement Learning in Dynamic Environments AI Agent Frontier

908 views - 2 years ago

Chi Jin-Talk Title: When Is Partially Observable Reinforcement Learning Not Scary?

Chi Jin-Talk Title: When Is Partially Observable Reinforcement Learning Not Scary? AI Agent Frontier

343 views - 3 years ago

Ding Zhao-Talk Title: Trustworthy Reinforcement Learning.

Ding Zhao-Talk Title: Trustworthy Reinforcement Learning. AI Agent Frontier

456 views - 3 years ago

Ilias Kazantzidis-Talk Title: Human-in-the-loop Safe Reinforcement Learning.

Ilias Kazantzidis-Talk Title: Human-in-the-loop Safe Reinforcement Learning. AI Agent Frontier

289 views - 3 years ago

Martim Brandao-Talk Title: Are robots safe for everyone?

Martim Brandao-Talk Title: Are robots safe for everyone? AI Agent Frontier

214 views - 3 years ago

Michael Everett-Talk Title: Certifiable Learning Machines.

Michael Everett-Talk Title: Certifiable Learning Machines. AI Agent Frontier

665 views - 3 years ago

Sergey Levine-Talk Title: Safety in Reinforcement Learning by Leveraging Offline Data.

Sergey Levine-Talk Title: Safety in Reinforcement Learning by Leveraging Offline Data. AI Agent Frontier

1.7K views - 3 years ago

Simon Shaolei Du-Talk Title: When are Offline Two-Player Zero-Sum Markov Games Solvable?

Simon Shaolei Du-Talk Title: When are Offline Two-Player Zero-Sum Markov Games Solvable? AI Agent Frontier

227 views - 3 years ago

Zhehua Zhou-Talk Title: Safe Reinforcement Learning with Model Order Reduction Techniques.

Zhehua Zhou-Talk Title: Safe Reinforcement Learning with Model Order Reduction Techniques. AI Agent Frontier

288 views - 3 years ago

Yali Du-Talk Title: Decision Structure in Decentralized Multi-Agent Learning.

Yali Du-Talk Title: Decision Structure in Decentralized Multi-Agent Learning. AI Agent Frontier

356 views - 3 years ago