Researchers propose STEP-KTODER, a framework for code preference optimization that defines steps as module-level functions in decomposed multi-function programs and assigns binary correctness labels v…
A new arXiv paper (arXiv:2608.10333v1) introduces MERA, a method that improves small language models through multi-cycle adaptation, raising Qwen2.5-Coder-1.5B from 28.7% to 49.7% pass on held-out Hum…
Researchers propose DC-Leap, a training-free framework that accelerates Diffusion Large Language Models (dLLMs) by up to 53.19x on MBPP for long-sequence generation and up to 105.02x when combined wit…
DeepSeek V3 generally outperforms Claude 3.5 Sonnet on raw coding benchmarks like HumanEval and MBPP, especially in C++, Rust, and mathematical implementations, while Claude 3.5 Sonnet is considered s…
Researchers propose Trajectory-Aware Commit Gating (TACG), a training-free decoder for diffusion language models that uses trajectory-aware signals to decide when to commit tokens, improving accuracy …
Vibe coding—prompting an AI agent and shipping unread output—introduces a measurable defect tax that makes it unsuitable for mission-critical systems, with 45% of AI-generated code containing security…
A cloud architect evaluated four Chinese LLM families—DeepSeek, Qwen, Kimi, and GLM—in a multi-region production pipeline serving thousands of requests per second via Global API's unified endpoint. De…
Researchers have developed Fast-dLLM++, a training-free extension to diffusion large language models that accelerates inference by selecting parallel token commit sets based on the full sorted confide…
Researchers have introduced DeepSuite, a new benchmark for evaluating AI coding agents that tests them using short, natural-language prompts requiring complex solutions across entire code repositories…