21 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…
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Siyuan Huang, Pengyu Cheng, Haotian Liu +10
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…
From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
Yue Xu, Yutao Sun, Yihao Liu +7
Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a cons…
Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
Yutao Sun, Yanting Miao, Hao-Xuan Ma +8
Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adap…
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Chang Wu, Junfeng Fang, Houcheng Jiang +5
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deploym…
A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
Jingyu Lu, Yuhan Wang, Jianming Luo +15
More than a dozen spoken dialogue systems have recently claimed to be "full-duplex," yet the term has been used to describe substantially different capabilities. Existing surveys c…