3 papers
cs.CL2026
ASTER: Agentic Scaling with Tool-integrated Extended Reasoning
Xuqin Zhang, Quan He, Zhenrui Zheng +3
Reinforcement learning (RL) has emerged as a dominant paradigm for eliciting long-horizon reasoning in Large Language Models (LLMs). However, scaling Tool-Integrated Reasoning (TIR…
cs.LG2025
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia, Xiaoxia Wu, Jisen Li +12
The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We cl…
cs.LG2025
TorchAO: PyTorch-Native Training-to-Serving Model Optimization
Andrew Or, Apurva Jain, Daniel Vega-Myhre +10
We present TorchAO, a PyTorch-native model optimization framework leveraging quantization and sparsity to provide an end-to-end, training-to-serving workflow for AI models. TorchAO…