4 papers
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
Wen Wang, Jiahua Bao, Tu Yongsiqi +8
We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated…
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
Ruoxi Cheng, Cheng Ruoxi, Ma Haoxuan +17
Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards provide either s…
EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
Ruoxi Cheng, Haoxuan Ma, Teng Ma +1
Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally, aligning LVLMs is not just a safety…
Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
Ruoxi Cheng, Haoxuan Ma, Weixin Wang +7
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with r…