https://zheng-bobo.github.io/en/tags/react/ Recent content in ReAct on Blowing in the wind Hugo -- gohugo.io en Tue, 11 Aug 2026 06:27:01 +0200 https://zheng-bobo.github.io/en/post/stanford-cs329a-self-improving-ai-agents/ Tue, 11 Aug 2026 06:27:01 +0200 https://zheng-bobo.github.io/en/post/stanford-cs329a-self-improving-ai-agents/ <p>Self-Improving AI Agent is not a mysterious system that recursively modifies itself indefinitely. A more practical understanding is: Agent forms a closed loop between generation, action, observation and verification, and uses the feedback obtained during reasoning to improve current answers, subsequent decisions, and even the next round of training.</p> <p>This article follows the main line of the Stanford CS329A course and strings together test-time calculations, verifiers, tool feedback, planning search, reinforcement learning, in-depth research and long-term evaluation into a complete framework.</p>