👋 Welcome to Yue’s blog

Note: This article is being updated. Please check back for the latest version. Recently, I participated in the FlashInfer AI Kernel Generation Contest (FlashInfer Contest, 2026). This blog post is not a tutorial on CUDA kernel optimization, and I am not a GPU operator development expert. My main purpose in joining the contest was to use a highly verifiable task environment with clear feedback to study how coding agents can continuously produce high-quality GPU kernels in a closed-loop workflow. The full technical report is Harness Engineering for LLM-Driven GPU Kernel Generation (Shui et al., 2026), and the public repository is mlsys26-flashinfer-contest. ...

A structural shift is underway in AI: the core capability of agents is moving from one-shot answer generation to continually producing verifiable, self-improving results in closed-loop systems. A representative milestone is DeepMind’s release of AlphaEvolve, an LLM-driven evolutionary coding agent that has delivered breakthroughs in mathematics, algorithm design, and engineering optimization, in several cases improving upon best-known human-designed baselines. Under this paradigm, the division of labor between humans and agents is clearly reconfigured: ...

By introducing DeepSeek Sparse Attention (DSA), a scalable reinforcement learning framework, and a large-scale agentic task synthesis pipeline, DeepSeek-V3.2 (DeepSeek-AI, 2025) achieves reasoning capabilities and agent performance comparable to GPT-5. Fig. 1. Benchmark of DeepSeek-V3.2 and its counterparts. (Image source: DeepSeek-AI, 2025) DeepSeek Sparse Attention Fig. 2. Attention architecture of DeepSeek-V3.2, where DSA is instantiated under MLA. (Image source: DeepSeek-AI, 2025) ...

From the evolution of the GPT series, researchers have gradually realized that as long as model parameters, training data, and compute resources are continuously scaled up, the performance of large models improves along a stable and predictable path. This predictability is characterized by Scaling Laws, which provide the theoretical foundation and practical confidence for high-cost pre-training. As model scale, alignment techniques, and inference-time compute co-evolve, the boundaries of AI capabilities are being systematically pushed. Scaling laws are not only the foundation for building next-generation models but also a key methodology for continuously improving model capabilities under compute constraints. ...

As Large Language Models (LLMs) achieve breakthroughs in natural language processing, their applications continue to expand. However, they also exhibit limitations such as knowledge cutoffs, hallucinations, and deficiencies in complex computation and logical reasoning. To address these challenges, Agentic RL, which combines agents with Reinforcement Learning (RL), is emerging as a key research direction. Agentic RL enables LLMs to possess capabilities like autonomous planning, decision-making, tool use, and environmental interaction by creating a closed-loop interaction with the external world (e.g., search engines, code interpreters, databases, browsers) and continuously optimizing through reward signals. In practical applications, it not only understands requirements and plans autonomously but also constantly corrects and optimizes within an execution-feedback loop. ...