NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
Efficient reinforcement learning with large language model priors.arXiv preprint arXiv:2410.07927
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A Graph Attention Network pretrained solely on synthetic MDPs solves held-out tabular RL benchmarks in context, outperforming UCB-VI and Q-learning online while matching VI-LCB offline.
LaGO improves online RL success rates over vanilla PPO by using pretrained LLMs as latent action priors, raising rates from 15.1% to 27.2% on CLEVR-Robot and 2.7% to 15.2% on Meta-World.
citing papers explorer
-
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
-
Reinforcement Learning Foundation Models Should Already Be A Thing
A Graph Attention Network pretrained solely on synthetic MDPs solves held-out tabular RL benchmarks in context, outperforming UCB-VI and Q-learning online while matching VI-LCB offline.
-
LaGO: Latent Action Guidance for Online Reinforcement Learning
LaGO improves online RL success rates over vanilla PPO by using pretrained LLMs as latent action priors, raising rates from 15.1% to 27.2% on CLEVR-Robot and 2.7% to 15.2% on Meta-World.