Peng Kuang — accepted AI-conference papers

2026

Agent Primitives: Reuseable Latent Building Blocks for Multi-Agent Systems

Haibo Jin, Peng Kuang, Ye Yu, Xiaopeng Yuan, Haohan Wang

ICML 2026poster

While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually crafted agent roles and interaction prompts, which leads to increased architectural complexity and limited reusability across…

Cited by 0 Source ↗Scholar ↗

2026

Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling

Peng Kuang, Yanli Wang, Xiaoyu Han, Yaowenqi Liu, Kaidi Xu, Haohan Wang

ICLR 2026poster

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority voting, which ignores PRM signals, occasionally outperforms st…

Cited by 0 Source ↗Scholar ↗