5 papers
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
Tiehua Mei, Minxuan Lv, Leiyu Pan +5
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces th…
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
Hongru Hou, Tiehua Mei, Denghui Geng +5
Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provide…
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Minxuan Lv, Tiehua Mei, Tanlong Du +9
We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL…
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv +7
Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribu…
GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems
Tiehua Mei, Hengrui Chen, Peng Yu +2
Although large language models (LLMs) have shown great potential in recommender systems, the prohibitive computational costs for fine-tuning LLMs on entire datasets hinder their su…