Guoteng Wang — accepted AI-conference papers

2026

PACE: Proactive Agent-Level Admission Control for Efficient Agentic Batch Inference

Qiaoling Chen, Zhisheng Ye, Tian Tang, Peng Sun, Boyu Tian, Guoteng Wang +4

ICML 2026poster

Batch inference for agentic workloads stresses the GPU key–value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as middle-phase thrashing, a previously under-characterized pathology in…

Cited by 0 Source ↗Scholar ↗

2026

Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Zhiheng Xi, Xin Guo, Yang Nan, Enyu Zhou, Junrui Shen, Wenxiang Chen +14

ICLR 2026poster

Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings—where stale data from past policies are used for training—improves sample efficiency, but remains challenging: policy entropy decline…

Cited by 0 Source ↗code ↗Scholar ↗