Selected Papers
Papers
Open-access papers. Commentary here; the full text is linked at the source. This site does not host PDFs.
2023 · ICLR · arXiv
ReAct: Synergizing Reasoning and Acting in Language Models
Reasoning and acting are one generation loop: the model thinks in language, acts on the world, and lets observations revise the next thought.
2023 · NeurIPS 2023 · arXiv
Reflexion: Language Agents with Verbal Reinforcement Learning
Reflexion reinforces language agents with verbal self-reflection and an episodic memory buffer; no weight updates, faster learning from trial-and-error.