EPISODE · May 3, 2025 · 11 MIN
RAGEN: train and evaluate LLM agents using multi-turn RL
from Large Language Model (LLM) Talk · host AI-Talk
RAGEN is a modular system for training and evaluating LLM agents using multi-turn reinforcement learning. Built on the StarPO framework, it implements the full training loop including rollout generation, reward assignment, and trajectory optimization. RAGEN serves as research infrastructure to analyze LLM agent training dynamics, focusing on challenges like stability, generalization, and the emergence of reasoning in interactive environments.
What this episode covers
RAGEN is a modular system for training and evaluating LLM agents using multi-turn reinforcement learning. Built on the StarPO framework, it implements the full training loop including rollout generation, reward assignment, and trajectory optimization. RAGEN serves as research infrastructure to analyze LLM agent training dynamics, focusing on challenges like stability, generalization, and the emergence of reasoning in interactive environments.
NOW PLAYING
RAGEN: train and evaluate LLM agents using multi-turn RL
No transcript for this episode yet
Similar Episodes
Feb 8, 2026 ·4m
Jan 30, 2026 ·6m
Dec 15, 2025 ·2m
Nov 30, 2025 ·5m
Oct 26, 2025 ·14m
Oct 26, 2025 ·61m