noahshinn/reflexion

Official code for Agent-Reflex: Teaching Language Agents to Act Reflectively

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

RL with Experience Replay

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Democratizing Reinforcement Learning for LLMs

mini project for nanorllm

[ICLR 2026] Official repository for the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"

[Neurips 2026] Official repository for the paper "Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models"