Large language models (LLMs) possess strong capabilities in language understanding and generation, as well as remarkable problem-solving abilities. In the educational domain, a representative application is to employ LLMs as learning assistants that answer students’ questions and support their learning processes. In such scenarios, it is crucial for the model to perceive a student’s cognitive level and provide explanations that are appropriate to that level. However, whether LLMs can effectively accomplish this task has not yet been thoroughly investigated. To address this gap, we introduce CogBench, an evaluation benchmark designed to assess the cognitive alignment capabilities of LLMs in educational QA. CogBench comprises 2.1K mathematics questions, each associated with multiple valid solutions that rely on knowledge and reasoning at different cognitive levels. Building on this structure, we formulate three cognition-aware evaluation tasks and propose three complementary metrics to quantify cognitive alignment from multiple perspectives. Extensive experiments on 11 representative LLMs reveal that, while models can often produce correct answers, they still struggle to consistently generate explanations that are aligned with the intended cognitive level. These results highlight substantial room for improvement and establish CogBench as a diagnostic benchmark for advancing cognitively aligned educational AI systems.

Diffusion language models (DLMs) are theoretically efficient but are limited by fixed-length decoding and poor compatibility with KV caches. Block diffusion mitigates these issues, yet still enforces a fixed block size and costly training. We introduce Next Sequence Prediction (NSP), which unifies next token and next block prediction, enabling the model to adaptively determine generation length at each step. NSP reduces to standard next token prediction when the length is one. Building on NSP, we propose the Sequential Diffusion Language Model (SDLM), which retrofits pretrained autoregressive language models (ALMs) at minimal cost. Specifically, SDLM performs diffusion inference within fixed-size mask blocks, but dynamically decodes contiguous subsequences based on model confidence, thereby preserving KV-cache compatibility and improving robustness to the varying uncertainty and semantics across the sequence. SDLM matches or surpasses strong autoregressive baselines with only 3.5M training samples, while achieving 2.0× 3.4× higher throughput than Qwen2.5 across three model scales (3B, 7B, 32B) with confidence-based decoding. Furthermore, when sampling with self-speculative decoding, SDLM attains up to 5.7× end-to-end speedup measured as wall-clock tokens per second (TPS). Notably, SDLM-32B achieves performance comparable to Qwen2.5-32B with up to 2.5× speedup, demonstrating the scalability of our approach. Project page and codes: https://github.com/OpenGVLab/SDLM