paper: Reflexion: Language Agents with Verbal Reinforcement Learning https://arxiv.org/abs/2303.11366 2023/10 https://nanothoughts.substack.com/p/reflecting-on-reflexion?utm_medium=email * https://promptengineering.org/reflexion-an-iterative-approach-to-llm-problem-solving/ 2023/5/9 * https://twitter.com/omarsar0/status/1762876215705162179 2024/2/29 * https://www.promptingguide.ai/techniques/reflexion - Self-Refine: Iterative Refinement with Self-Feedback https://arxiv.org/abs/2303.17651 - CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing https://arxiv.org/abs/2305.11738 - https://x.com/jerryjliu0/status/1786911108823224796 - llamaindex 有實作 - 用外部工程提供回饋來反思，例如用 搜尋引擎 * langchain * Reflexion: Language Agents with Verbal Reinforcement Learning https://twitter.com/LangChainAI/status/1760729261961564429 2024/2/23 * langgraph code: https://github.com/langchain-ai/langgraph/blob/main/examples/reflexion/reflexion.ipynb