Reflexion: Language Agents with Verbal Reinforcement Learning
Source
- Person key:
ysymyth - Source kind:
paper - Canonical URL: https://arxiv.org/abs/2303.11366
- License:
NOASSERTION - Public handling:
public-metadata-summary-hash-link-only - Semantic hash:
28a7ce69da83e95cfa8f6da17af6faad59a17d1439eb3b22a40d76e7eff85ca8 - First seen: 2026-05-16
- Last changed: 2026-05-16
- Identity guard: Do not confuse with yao-shunyu-alfred, the physics-to-AI researcher at alfredyao.github.io.
Classification
- Category: Language agents / agent architectures
- Topic hub: shunyu-yao-public-corpora
- Project taxonomy: shunyu-yao-project-taxonomy
- Paper map: shunyu-yao-paper-map
Summary
Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretel…
What This Teaches
How language models become agents through reasoning, acting, memory, tools, and interface design.
Related
Public Handling Notes
- EXTRACTED: Metadata and links are from public sources.
- INFERRED: Unclear-license full text, PDFs, and source code should not be mirrored into public wiki pages.
- AMBIGUOUS: Items discovered by keyword search are still separated by source identity and category heuristics.