10 papers
Anytime Safe PAC Efficient Reasoning
Chengyao Yu, Hao Zeng, Youxin Zhu +3
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies im…
GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning
Yanyan Wu, Boyi Zhang, Yanlin Liu +10
Financial portfolio trading is naturally formulated as a reinforcement learning problem, where an agent sequentially rebalances assets under changing market conditions to balance r…
GLM-5: from Vibe Coding to Agentic Engineering
GLM-5-Team, :, Aohan Zeng +184
We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (AR…
Conditional Performance Guarantee for Large Reasoning Models
Jianguo Huang, Hao Zeng, Bingyi Jing +2
Large reasoning models have shown strong performance through extended chain-of-thought reasoning, yet their computational cost remains significant. Probably approximately correct (…
SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs
Ruixuan Huang, Hao Zeng, Hantao Huang +4
Post-training quantization (PTQ) plays a crucial role in the democratization of large language models (LLMs). However, existing low-bit quantization and sparsification techniques a…
A note on conditional PAC-efficient reasoning in large language model routing
Hao Zeng, Bingyi Jing
We study distribution-free risk control for model routing, motivated by large language model reasoning. We formalize pointwise conditional efficiency under a probably approximately…