Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code

Covers three core methods for grounding agents in tool and execution feedback: ReAct, RLEF and self-critique. A structured foundation for engineers building coding agents with test-based feedback loops.

• grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.

• videoStanford CS329A Self-Improving AI Agents | Part 5 | Planning and Multi-Step Reasoning
• videoStanford CS153 Frontier Systems | The Discipline of Delivering Value per Gigawatt
• videoStanford CS25: V5 I On the Biology of a Large Language Model, Josh Batson of Anthropic
• videoStanford CS336 Language Modeling from Scratch | Spring 2025 | Overview and Tokenization

• videoStanford CS329A Self-Improving AI Agents | Part 5 | Planning and Multi-Step ReasoningStanford Online
• articleReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao et al.
• videoStanford CS329A Self-Improving AI Agents | Part 2 | Test-Time Compute ScalingStanford Online

Checking sign-in…

Loading comments…