6 papers
DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning
Chuzhan Hao, Wenfeng Feng, Yuewei Zhang +1
Multi-step agentic retrieval systems based on large language models (LLMs) have demonstrated remarkable performance in complex information search tasks. However, these systems stil…
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…
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Wenfeng Feng, Penghong Zhao, Guochao Jiang +4
Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely he…
AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation
Wenfeng Feng, Chuzhan Hao, Yuewei Zhang +3
Leveraging the autonomous decision-making capabilities of large language models (LLMs) has demonstrated superior performance in reasoning tasks. However, despite the success of ite…
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
Weiqing Li, Guochao Jiang, Xiangyong Ding +5
Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the…
RASD: Retrieval-Augmented Speculative Decoding
Guofeng Quan, Wenfeng Feng, Chuzhan Hao +3
Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens r…