arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2026-08-26 至 2026-08-26 共收录 2 信号源:cs.CL, cs.AI, cs.LG

1. 代码与定理证明 2 篇

2608.23644 2026-08-26 cs.AI 新提交 57%

Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value

伦理大语言模型辅助研究:负责任委托、验证与认知价值框架

Kalin Stoyanov

机构 * University of Chemical Technology and Metallurgy(化工技术与冶金大学)

专题命中 代码与定理证明 :reasoning(abstract);分类 cs.AI

AI总结 本文构建了伦理LLM辅助研究的规范性框架,明确其伦理边界由充分验证与可问责人类所有权决定,提出认知审计概念以实现AI辅助推理的透明可审查性。

Comments This is a substantially revised version of submit/7664457. I have extensively revised the manuscript to clarify its scholarly contribution, strengthen the formal framework and literature grounding, and remove or reformulate claims that were not sufficiently supported

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16978 2026-08-26 cs.MA 版本更新 56%

Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM Agents

Lark:生物启发的多利益相关者大语言模型代理神经进化

Rikhil Tanugula, Dheeraj Chintapalli, Sunkalp Chandra

专题命中 代码与定理证明 :reasoning(abstract,comments)

AI总结 Lark通过结合大语言模型推理与进化型多智能体系统,解决冗余与利益相关者权衡问题,采用四机制提升策略生成效率与透明度,实验显示其在30轮评估中表现优异且成本可控。

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: NeurIPS 2025 Workshop on Efficient Reasoning

详情

展开后加载摘要…

URL PDF HTML 收藏