3 citations · 5 across the 14 of their papers we have counts for
7 papers · 1 filter
AReaL-TIK: Stateful Agentic Optimization of Unified RL Kernels through an Optimization IR
Ran Yan, Youhe Jiang, Jiayi Nie +5
Reinforcement learning (RL) post-training often uses distinct GPU kernels for rollout and policy update. In synchronous PPO and GRPO, numerical disagreement can perturb ratios betw…
AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning
Yingqi Peng, Jiawei Zhang, Wenhao Zhou +7
Online agentic reinforcement learning implemented with micro-services separates policy training from rollout generation, improving scalability and modularity while potentially maki…
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents
Ran Yan, Wei Fu, Jiale Li +21
LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally stati…
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
Liyuan Zhang, Jiarui Zhang, Jinwei Yao +6
Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass. Recent diffusio…
HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware
Yan Liang, Youhe Jiang, Ran Yan +3
Long-context training of large language models (LLMs) is commonly distributed with Context Parallelism (CP) and Head Parallelism (HP), but existing training systems largely assume…
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Youhe Jiang, Ran Yan, You Peng +4
Modern Large Language Model (LLM) serving operates in highly volatile environments characterized by severe runtime dynamics, such as workload fluctuations and elastic cluster autos…
AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
Jiarui Zhang, Yuchen Yang, Ran Yan +8
Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long tok…