探索自精炼流程中非对称容量分配策略，揭秘资源优化与推理效率的关键突破。
arXiv:2608.21345v1 Announce Type: new Abstract: Self-refinement, typically structured as generation, critique, and revision, is a widely adopted parad…
精炼铜正以至少12年来的最快速度疯狂涌入美国，因全球贸易商正赶在美国总统特朗普就精炼铜进口关税作出决定之前提前布局。根据IHS Markit可追溯至2014年的海运数据，今年7月有超过20万吨的铜抵达美国，刷新了有记录以来的单月最高流入纪录。这一波进口狂潮将进一步推高过去一年中建立起来的庞大美国铜库…
用进化算法迭代精炼价值，提升大模型解码质量，被ACL 2026接收的前沿研究。
arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alte…
首个评估数据精炼配方组合与顺序敏感执行的基准，直击大模型数据处理链条的可靠性盲区
arXiv:2606.31435v1 Announce Type: new Abstract: Data refinement involves executing multi-step recipes over evolving text states, where both compositio…
用符号反馈替代人工标注，让大模型在迭代自精炼中提升规划可靠性与鲁棒性，值得关注。
arXiv:2606.27757v1 Announce Type: new Abstract: Large language models (LLMs) have attracted widespread attention from academia and industry, yet their…
离线择优与在线自精炼生成结合，为LLM微调提供双层数据策展新范式。
arXiv:2511.21056v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) datasets are critical to the downstream performance of large language…
提出AURA方法，通过自适应不确定性感知精炼解决LLM裁判审计难题，显著提升评估可靠性。
arXiv:2606.19714v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges for open-ended generation, as large-sca…
从隐状态层面精炼LLM推理过程，开源代码助力提升模型可靠性。
arXiv:2606.17524v1 Announce Type: new Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain u…
提出轨迹精炼蒸馏新方法，提升大模型知识迁移效果
arXiv:2606.08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs),…
前沿研究提出细粒度诊断反馈，精准定位LLM代码中的bug并给出改进建议
arXiv:2606.03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs. Existing methods rely on feedback signals such …
新型扩散语言模型并行解码方法DMax，通过自精炼机制减少误差累积，实现高并行度高质量生成。
arXiv:2604.08302v3 Announce Type: replace-cross Abstract: We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigate…