7 papers
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Bingxi Hou, Guochao Jiang, Guofeng Quan +4
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories.…
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Tingyun Li, Wenfeng Feng, Weiqing Li +3
Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate par…
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Guochao Jiang, Jingyi Song, Guofeng Quan +3
Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an…
Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
Chuzhan Hao, Wenfeng Feng, Guochao Jiang +3
Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external…
Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval
Weiqing Li, Jinyue Guo, Yaqi Wang +4
Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-inte…
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization
Haiyang Xiao, Weiqing Li, Jinyue Guo +3
Although post-training quantization (PTQ) provides an efficient numerical compression scheme for deploying large language models (LLMs) on resource-constrained devices, the represe…
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Guochao Jiang, Wenfeng Feng, Guofeng Quan +4
Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning meth…