Multi-turn RL improves LLM agent long-horizon performance
Agentic RL gains concentrate in error recovery and long-horizon tasks but require sufficient interaction budgets.
Stories per day · 30 days
Relatedgrpo1huggingface1llm-agents1multi-turn1reinforcement-learning1reward-model1streaming-video1turn-wise1video-generation1
6 stories, newest first · one card per story
Stories tagged #rl
TurnWise improves streaming video RL with turn-level credit
TurnWise assigns turn-level advantages using silence-completed prefix scoring to reduce redundancy in streaming video policy learning
EmoReward self-evolving reward calibration advances emotional video RL
EmoReward distills reliability from training traces to adaptively allocate weights for facial motion and chromatic cues in video generation.
Personal-Agent Mediated Recommendation with Cross-Platform User History
PAMO trains personal LLM agents to re-rank platform recommendations using cross-platform history with fewer harmful overrides.
Welcome RL Environments to the hub
Hugging Face is adding reinforcement learning environments to the Hub.
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
A paper on Hugging Face's daily papers describes FP8 reinforcement learning challenges and proposes a solution to fix training instability in LLMs.