新用户从这里开始
- 先选订阅词（如 RAG、multimodal、Agent），每周自动看到相关新论文。
- 在列表页点开感兴趣论文，点击“赞助解读”得到结构化结论与可执行动作。
- 把高价值解读分享到团队/社群，协同节省阅读成本。
每周精选
近7天内社区解读较多的方向与热门关键词，适合先读一眼再决定是否深入。
以下为全部论文，未做任何筛选。
| 标题 | arXiv | 发布时间 | 状态 |
|---|---|---|---|
|
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Tianjie Ju, Zheng Wu, Yueqing Sun, Yuhan Cui, Bobo Li, Shengqiong Wu, Pengzhou Cheng, Haodong Zhao, Zongru Wu, Xinbei Ma, Doris Zhang, Kunling Li, Mong-Li Lee, Wynne Hsu, Hao Fei, Qi Gu, Gongshen Liu, Zhuosheng Zhang
cs.CV
cs.CV
|
2608.27456v1 | 2026-08-27 17:59:33 | 待赞助 |
|
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
Yufan Wu, Yinghui He, Zhengyi Hu, Lang Wei, Ruichen Li, Qifan Yang, Ting Zhu
cs.CL
cs.CL
|
2608.27455v1 | 2026-08-27 17:59:30 | 待赞助 |
|
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu
cs.AI
cs.AI
cs.CL
|
2608.27454v1 | 2026-08-27 17:59:11 | 待赞助 |
|
Tacet: A Language and Type System for Automatic Statistical Validity Accounting
Chiké Abuah
cs.PL
cs.PL
cs.SE
|
2608.27451v1 | 2026-08-27 17:59:01 | 待赞助 |
|
SWE-Prime: Fewer Trajectories, Better Performance
Dewu Zheng, Ruizhe Ye, Yanlin Wang, Yang Ye, Hongyu Zhang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jianxing Yu, Zibin Zheng
cs.SE
cs.SE
cs.AI
cs.CL
|
2608.27449v1 | 2026-08-27 17:58:10 | 待赞助 |
|
TTPO: Test-Time Policy Optimization
Aozhe Wang, Zhengxi Lu, Jianze Wang, Shangke Lv, Ying Liu, Weiming Lu, Jun Xiao, Yueting Zhuang, Hua Yang, Qianglong Chen, Yongliang Shen
cs.CL
cs.CL
|
2608.27448v1 | 2026-08-27 17:58:10 | 待赞助 |
|
Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?
Ting Yan
cs.HC
cs.HC
cs.CR
|
2608.27443v1 | 2026-08-27 17:56:38 | 待赞助 |
|
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
Dewu Zheng, Yanlin Wang, Xiwen Wang, Kefeng Duan, Hongyu Zhang, Xilin Liu, Yuchi Ma, Zibin Zheng
cs.SE
cs.SE
cs.AI
cs.CL
|
2608.27442v1 | 2026-08-27 17:56:24 | 待赞助 |
|
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo, Changsheng Chen, Haoliang Li
cs.CR
cs.CR
cs.AI
|
2608.27439v1 | 2026-08-27 17:55:33 | 待赞助 |
|
Disjoint and nearly disjoint sums of matrix multiplication tensors and their centroids
Martin Kassabov, J. M. Landsberg, Victor Souza, Philip Speegle
math.AG
math.AG
cs.CC
math.AC
|
2608.27434v1 | 2026-08-27 17:53:45 | 待赞助 |
|
Factorized Boolean representations for efficient quantum synthesis
Mehul Shah, Robert Fiszer, Marek Perkowski
quant-ph
quant-ph
|
2608.27430v1 | 2026-08-27 17:52:31 | 待赞助 |
|
Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong, Philippe Schwaller
cs.AI
cs.AI
|
2608.27429v1 | 2026-08-27 17:50:44 | 待赞助 |
|
Stochastic Estimation of Transduced Language Models
Vésteinn Snæbjarnarson, Samuel Kiegeland, Manuel de Prada Corral, Ryan Cotterell, Tim Vieira
cs.CL
cs.CL
|
2608.27428v1 | 2026-08-27 17:50:21 | 待赞助 |
|
Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit
Yisen Xi
cs.SE
cs.SE
cs.AI
|
2608.27427v1 | 2026-08-27 17:50:07 | 待赞助 |
|
Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
Qianlong Lan, Vinothini Pandurangan, Anuj Kaul, Indranil Sanyal
cs.CR
cs.CR
cs.AI
|
2608.27424v1 | 2026-08-27 17:49:28 | 待赞助 |
|
misi: a Metric Inverted Sample Index
Edgar Chavez
cs.IR
cs.IR
|
2608.27422v1 | 2026-08-27 17:48:22 | 待赞助 |
|
Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
Kevin Zhu, Ryan Zhang, Baraa Abed, Tilendra Choudhary, Malvern Madondo, Mehak Arora, Yixuan Yang, Alasdair Gent, Aditya Nagori, Omer T. Inan, Krista L. Haines, Patrick Georgoff, Suresh M. Agarwal, Vijay Krishnamoorthy, Tetsu Ohnuma, Mihai V. Podgoreanu, Michael R. Pinsky, Gilles Clermont, Craig M. Coopersmith, Craig S. Jabaley, Rishikesan Kamaleswaran
cs.AI
cs.AI
cs.LG
|
2608.27421v1 | 2026-08-27 17:46:21 | 待赞助 |
|
Boosting LLM Exploration via Weak-Model Guidance in RLVR
Xingyu Shen, Huishuai Zhang, Peng Li, Yinchun Wang, Dongyan Zhao
cs.CL
cs.CL
|
2608.27420v1 | 2026-08-27 17:45:50 | 待赞助 |
|
Algorithms for Robbins' Problem using Markov Decision Processes
Léonard Brice, F. Thomas Bruss, Anirban Majumdar, Jean-François Raskin
cs.GT
cs.GT
math.PR
|
2608.27419v1 | 2026-08-27 17:45:28 | 待赞助 |
|
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung
cs.CV
cs.CV
|
2608.27417v1 | 2026-08-27 17:43:58 | 待赞助 |