新方法分解不确定性，让LLM代理主动提问澄清，提升交互可靠性。
arXiv:2606.19559v1 Announce Type: new Abstract: Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insuffici…
研究发现大语言模型在道德判断中表现出“方向盲从”：无论指令对错，模型都会盲目遵从，揭示AI伦理漏洞。
arXiv:2606.14037v1 Announce Type: new Abstract: As language models take integrated roles across many domains, the response of LLMs to user pushback be…
LLM智能体悄然失败？新研究用干预法精准定位错误根源，让沉默不再失控。
arXiv:2606.09071v1 Announce Type: new Abstract: Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet …
直方图损失在回归任务中的应用原理与效果深入探究，为损失函数设计提供新视角
arXiv:2402.13425v3 Announce Type: replace Abstract: It is becoming increasingly common in regression to train neural networks that model the entire di…
提出注意力引导微调方法，显著提升多模态大模型的思维链推理效果，是前沿研究新突破。
arXiv:2606.01558v1 Announce Type: new Abstract: The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) rema…
专用护栏系统的威胁分类新框架，为AI安全防护提供系统性风险评估方法
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse re…
农业场景下多模态大模型也会“看走眼”？这篇论文深入分析了AI在解读和生成农业图像时的幻觉行为，值得从业者警惕。
arXiv:2605.27595v1 Announce Type: cross Abstract: Large Language Models (LLMs) are being rapidly adopted in agricultural imaging applications, ranging…
这篇论文揭示AI替代人力的短期效率提升，实则埋下长期能力丧失的隐患，是反思技术与社会关系的必读研究。
arXiv:2605.27399v1 Announce Type: cross Abstract: What looks like acceleration can be a quiet transfer of burden from the present to the future. Attem…
从拉普拉斯算子视角重新定义键盘布局，突破传统线性思维的学术探索
arXiv:2602.07730v2 Announce Type: replace Abstract: Across scientific disciplines, Laplacian eigenvectors serve as a fundamental basis for simplifying…
直达前沿AI记忆系统研究论文，评估LLM在多社交群组中的表现，洞察AI记忆适配瓶颈
arXiv:2605.17789v1 Announce Type: new Abstract: Memory systems for AI assistants were built for single-user dialogue and fail characteristically when …