揭秘专用裁判与共享评判的取舍之道，为LLM评估定制最优策略，实验详实、图表清晰。
arXiv:2607.27984v2 Announce Type: replace Abstract: Agentic systems generate outputs faster than human review. We contrast two LLM evaluator specializ…
SpotOptim优化器新工作论文，十八页篇幅系统介绍方法思路，技术细节与理论分析兼备，值得算法研究者关注。
arXiv:2604.13672v2 Announce Type: replace Abstract: The spotoptim package implements surrogate-model-based optimization of expensive black-box functio…
AI对齐不完美时，价值系统有多脆弱？这篇论文用严谨分析揭示潜在风险，值得关注。
arXiv:2607.28881v1 Announce Type: new Abstract: As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that …
深入探讨为何智能体AI离不开可预测的确定性环境，为规模化应用筑牢理论根基
arXiv:2606.22495v1 Announce Type: new Abstract: Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-…
全新智能体策略优化方法APPO，推动强化学习前沿发展
arXiv:2606.12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn to…
六层容错机制让大模型编码代理写入更可靠，不再默默失败
arXiv:2604.10842v3 Announce Type: replace-cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context …
探索用大语言模型在结构引导下实现高效符号回归的突破方法
arXiv:2606.07704v1 Announce Type: new Abstract: Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to gui…
提出VeriCache方法，将有损KV Cache转化为无损LLM推理，提升模型效率与精度。
arXiv:2605.17613v1 Announce Type: cross Abstract: The large size of the KV cache has become a major bottleneck for serving LLMs with increasing contex…
提出“Metis AI”新概念，揭示数字任务中AI失效的隐秘界限，挑战传统物理/数字二分法
arXiv:2605.14407v1 Announce Type: new Abstract: The dominant discourse on AI limitations frames the boundary of AI capability as a divide between digi…