6 papers · 1 filter
Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
Yixiao Zhou, Yang Li, Dongzhou Cheng +2
Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather th…
Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
Junbo Li, Peng Zhou, Rui Meng +3
Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Re…
Grokked Models are Better Unlearners
Yuanbang Liang, Yang Li
Grokking-delayed generalization that emerges well after a model has fit the training data-has been linked to robustness and representation quality. We ask whether this training reg…
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tas…
Policy Guided Tree Search for Enhanced LLM Reasoning
Yang Li
Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought pro…
LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing
Yang Li
The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, sele…