1
AI 灌水稿激增：预印本平台 arXiv 出台新规，每人每月限投 2 篇
IT之家 10 月 2 日消息，预印本开放获取平台 arXiv 发布博文，宣布于昨日（10 月 1 日）开始实施全新速率限制政策， 将所有投稿者每月提交上限设为 2 篇、同时在审活跃稿件上限设为 3 篇。 IT之家注：arXiv 于 1991 年 8 月 14 日由理论物理学家 Paul Ginsp…
2
From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems
聚合前沿论文的预印本平台，第一时间追踪AI研究动态，科研追新必备利器。
arXiv:2608.07627v1 Announce Type: new Abstract: Hospitals are racing to embed AI, while coping with the surge in adaptation of the technology in other…
3
Terminal Agents Suffice for Enterprise Automation
重磅预印本！终端智能体或将成为企业自动化的最优解，51页详实论证，AI Agent落地方向必读。
arXiv:2604.00073v3 Announce Type: replace-cross Abstract: There has been growing interest in building agents that can interact with digital platforms …
4
Tokenizer-Agnostic Engram Module
突破传统分词限制，提出与分词器无关的记忆模块，为语言模型的长效记忆与跨词元建模提供新思路。
arXiv:2607.29065v1 Announce Type: new Abstract: Deepseek's Engram, a conditional memory module, was introduced to trade-off storage versus reasoning i…
5
Environment-free Synthetic Data Generation for API-Calling Agents
一站式获取海量最新学术预印本，免费开放，助你追踪AI、计算机等前沿研究动态，科研效率拉满
arXiv:2607.16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality traject…
6
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
从加权模型平均视角重新审视异构LLM合并，提供理论分析与新方法，适合模型集成研究者。
arXiv:2607.18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted a…
7
Cura 1T: Specialized Model for Agentic Healthcare
专为医疗场景打造的1T参数大模型，开启智能体医疗新范式。
arXiv:2607.15314v1 Announce Type: new Abstract: Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized …
8
Troubling new details emerge on diabetes ouster controversy
美国糖尿病协会被曝阻挠评论文章发表，作者无奈转投预印本，科学出版的审查争议再添新证。
American Diabetes Association blocked publication of op-ed articles so the authors posted them as a preprint.
9
Index SLM Technical Report
arXiv 让你免费获取最新学术论文预印本，无需订阅即可一键下载 PDF，追踪前沿研究。
arXiv:2607.09885v1 Announce Type: new Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series compri…
10
Interaction Techniques that Encourage Longer Prompts Can Improve Psychological Ownership when Writing with AI
一站式获取最新AI与交互论文，免费阅读PDF，预印本抢先看。
arXiv:2507.03670v2 Announce Type: replace-cross Abstract: Writing longer prompts for an AI assistant to generate a story increases psychological owner…
11
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
直达最新AI软件工程论文，支持PDF下载与格式切换，学术引用管理一步到位。
arXiv:2607.02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles. Large…
12
Agent Safety Is Action Alignment
免费获取最新AI论文预印本，一键检索和阅读前沿研究，是科研工作者跟踪学术动态的高效利器。
arXiv:2606.28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and sen…
13
Code evolution for link prediction in complex networks
arXiv预印本平台汇集最新科研论文，开源免费，一键下载，助你高效追踪学术前沿。
arXiv:2606.26132v1 Announce Type: cross Abstract: The problem of predicting links in complex networks appears in different disciplines and has led to …
14
AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reported Breakdowns
海量预印本论文免费获取，每日更新AI、医学等前沿研究，是快速追踪最新学术动态的必备资源库。
arXiv:2606.27302v1 Announce Type: cross Abstract: AI healthcare chatbots are increasingly used to support health information seeking and self-manageme…
15
Refusal Lives Downstream of Persona in Chat Models
arXiv.org全球学术论文预印本平台，免费获取最新研究成果，开放共享加速科学传播。
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in inst…
16
Modular Diffusion Models for Structured Visual Recognition
查论文、下PDF，全球科研人都在用的AI预印本库，最新成果第一时间掌握。
arXiv:2606.22702v1 Announce Type: new Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, se…
17
Source-Grounded Data Generation for Text-to-JSON Learning
直达最新Text-to-JSON学术研究，免费下载PDF，一键获取引用与相关论文，科研必备入口。
arXiv:2606.20072v1 Announce Type: new Abstract: From financial filings to clinical records, legacy industries rely heavily on long, unstructured docum…
18
Diffusion Language Models: An Experimental Analysis
全球最大的学术预印本平台，免费获取最新论文，支持PDF下载与引用导出，科研必备。
arXiv:2606.19475v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, …
19
DIPHINE: Diffusion-based $\Phi$-ID Neural Estimator
arXiv预印本，DIPHINE论文在此，前沿扩散模型理论免费看
arXiv:2606.18997v1 Announce Type: new Abstract: Uncovering the true informational architecture of real-world complex systems requires disentangling ho…
20
TRACE: Learning to Compute on Circuit Graphs
轻松检索和阅读最新预印本论文，支持全文下载和引用管理，学术研究必备在线工具。
arXiv:2509.21886v3 Announce Type: replace Abstract: Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundame…