noahshinn/reflexion
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
This project helps researchers and developers explore how language models can improve their reasoning and decision-making by learning from their mistakes. It takes a language model agent and a set of questions or tasks as input, then outputs improved answers or actions by enabling the agent to reflect on its previous attempts. This is for AI researchers and practitioners who are experimenting with advanced language model agents.
3,093 stars. No commits in the last 6 months.
Use this if you are developing or studying advanced AI agents and want to experiment with methods that allow them to self-correct and improve their performance on complex reasoning or decision-making tasks.
Not ideal if you are looking for a plug-and-play solution for general language model applications without a focus on agent-based learning and self-reflection.
Stars
3,093
Forks
298
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/noahshinn/reflexion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is...
sotopia-lab/sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
zhudotexe/redel
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive...
TIGER-AI-Lab/verl-tool
A version of verl to support diverse tool use
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning