LLM推理新突破：HippoSpark按需经验系统，动态提升复杂推理准确率与效率。
arXiv:2606.29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has beco…
端侧大模型推理的能耗难题有了新解法，EnerInfer提出能源感知优化框架，兼顾性能与功耗，适合部署在手机等边缘设备。
arXiv:2606.23001v1 Announce Type: cross Abstract: On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effect…
揭秘LLM推理效率新思路：最小干预即可显著提升性能，少即是多！
arXiv:2510.13940v4 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve …
NVIDIA推出的高性能推理加速器，专为长时间运行AI代理设计，速度更快、效率更高。
Powers faster, efficient reasoning for long-running agents Discussion | Link
arXiv最新论文提出跨语言推测解码方法，无需目标语言训练数据即可加速多语言大模型推理
arXiv:2605.30580v1 Announce Type: cross Abstract: Speculative decoding has become a crucial component of large language model (LLM) inference, enablin…
提出 OBCache 最优脑剪枝方法，精准削减 KV 缓存，让长上下文大模型推理又快又省内存。
arXiv:2510.07651v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but …
提出原位反馈方法，让专家在对话中逐轮优化LLM输出，提升多轮协作的可靠性。
arXiv:2510.00777v2 Announce Type: replace Abstract: LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that mod…
挑战LLM层冗余传统假设，揭示校准策略比搜索算法更关键
arXiv:2604.24938v3 Announce Type: replace-cross Abstract: Depth pruning improves the inference efficiency of large language models by removing Transfo…
探索推理时对齐与执行轨迹的新方法，为AI系统行为优化提供理论框架。
arXiv:2605.21516v1 Announce Type: cross Abstract: Harness engineering has emerged as an important inference-time technique for large language model (L…
教你如何让小型语言模型学会判断何时该“求救”，避免盲目依赖昂贵大模型，提升Agent系统效率的突破性研究。
arXiv:2605.16604v1 Announce Type: new Abstract: Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheape…