综述LLM推理范式：快思考、慢思考与工具增强如何协同进化
arXiv:2508.12265v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse dom…
先解释后探索，SPHINX提出全新AI推理范式
arXiv:2606.17482v1 Announce Type: new Abstract: Generating adversarial driving scenarios is critical for evaluating and improving autonomous vehicle d…
用“周期表”系统梳理LLM推理的范式、方法与失败模式，结构清晰，综述全面，值得研究者细读。
arXiv:2606.11470v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across natural language processing tasks…
提出Vision Inference Former方法，解决多模态大模型视觉一致性难题，为视觉-语言融合提供新范式。
arXiv:2605.18160v1 Announce Type: new Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily…