1
京东JoyInside戴文军：AI的终极形态不是聊天，是融入你家每一件物品丨AIGC2026
京东高管直言AI终极形态：硬件主动融入生活，而非仅聊天互动，重新定义智能家居未来。
硬件不该让人适应，它应该主动适应你
2
Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs
用27,000+条Slack消息测试七款大模型，看AI能否从聊天记录猜出员工“知道什么”
arXiv:2605.22971v1 Announce Type: new Abstract: Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses…
3
"Would You Want an AI Tutor?" Understanding Stakeholder Perceptions of LLM-based Systems in the Classroom
论文揭示学生、教师等利益相关者对AI导师的真实态度，为课堂部署大模型系统提供关键洞察。
arXiv:2503.02885v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have gained traction in educational settings, often framed as v…
4
Guidelines for Human-AI Interaction
微软20年人机交互研究结晶，AI交互设计必读指南
Article URL: https://www.microsoft.com/en-us/research/project/guidelines-for-human-ai-interaction/ Comments URL: https://news.ycombinator.com/item?id=…
5
Measuring and mitigating overreliance to build human-compatible AI
探讨如何量化并缓解人类对AI的过度依赖，为构建真正人机兼容的智能系统提供新思路
arXiv:2509.08010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) distinguish themselves from previous technologies by functionin…
6
Toward User Comprehension Supports for LLM Agent Skill Specifications
这篇论文探讨如何通过技能规格说明帮助用户准确理解LLM Agent的边界，基于878个网络安全技能的分析。
arXiv:2605.19362v1 Announce Type: cross Abstract: Users often interpret and select agent skills through their \texttt{SKILL.md} specifications. To pro…
7
MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness
KDD 2026发布最新基准MirrorBench，重新定义对话代理拟人化评估标准，推动人机交互研究新高度
arXiv:2601.08118v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as human simulators, both for evaluating …
8
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
首个大规模真实人机对话数据集，捕捉用户对话背后的想法，揭示LLM交互中的思维过程。
arXiv:2605.20087v1 Announce Type: new Abstract: Conversational AI has now reached billions of users, yet existing datasets capture only what people sa…
9
When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
人类将认知自我调节外包给大模型，48小时内系统崩溃——揭示LLM交互系统的架构限制与元认知共选问题。
arXiv:2604.15343v2 Announce Type: replace-cross Abstract: We report a detailed autoethnographic case study of a single-subject who deliberately constr…
10
Alignment Drift in Long-Term Human-LLM Interaction: A Mechanism-Oriented Framework
揭示长期人机交互中LLM对齐漂移机制，提出全新框架防范AI失控。
arXiv:2605.16516v1 Announce Type: cross Abstract: Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which…
11
Your AI Use Is Breaking My Brain
直击AI写作对互联网的扭曲，提出“僵尸互联网”概念，反思人机交互的困境与认知疲劳。
Your AI Use Is Breaking My Brain Excellent, angry piece by Jason Koebler on how AI writing online is becoming impossible to avoid, filtering it is men…
12
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
用脑电图揭示人脑如何识别或误信AI生成幻觉，神经机制首次解密
arXiv:2605.16953v1 Announce Type: cross Abstract: While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by wh…
13
Improve Large Language Model Systems with User Logs
利用用户交互日志实现大语言模型持续学习，突破数据稀缺与算力瓶颈的新范式。
arXiv:2602.06470v2 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models…
14
Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas
把线性LLM对话变成空间画布上的分支交互，解决备选探索和长对话管理难题。
arXiv:2605.15848v1 Announce Type: cross Abstract: Conversational interfaces powered by large language models (LLMs) are widely used for ideation and a…
15
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
大模型“读心术”提升是否真能改善人机交互？来自互动评估的实证发现，挑战常规认知。
arXiv:2605.15205v1 Announce Type: new Abstract: Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective…