6 papers
CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
Yifan Yu, Moyan Li, Shaoyuan Xu +4
Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes…
XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
Udbhav Bamba, Minghao Fang, Yifan Yu +2
Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existi…
Introspective Diffusion Language Models
Yifan Yu, Yuqing Jian, Junxiong Wang +12
Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR mo…
OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
Kaizhuo Yan, Yingjie Yu, Yifan Yu +2
Proximal Policy Optimization (PPO)-based reinforcement learning from human feedback (RLHF) is a widely adopted paradigm for aligning large language models (LLMs) with human prefere…
IC-Cache: Efficient Large Language Model Serving via In-context Caching
Yifan Yu, Yu Gan, Nikhil Sarda +7
Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-wo…
Single-agent or Multi-agent Systems? Why Not Both?
Mingyan Gao, Yanzi Li, Banruo Liu +4
Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy…