Week 41Oct 5 to Oct 11, 2026

AI papers, week by week

The most voted AI research papers of every week since 2023. Find them by topic, year or week, and open any paper in one click.

Papers: 2,659
Weekly issues: 178
Since: 2023

Paper of the week

01Sep 30, 2026Reasoning and agents

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Arman Behnam, Sunglyoung Kim, Jiayi Yu and 2 more

The most voted paper of the week, with 283 votes.

Read the paper On arXiv

This week 15 papers

View the full issue

02
AgentGarten: Code Worlds for Evolving Agents
Jiawei Chi, Shangchen Miao, Zhiyuan Shi and 11 more
Oct 7, 2026257 votesarXiv 2610.12374
Vision
03
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
Bingxi Hou, Guochao Jiang, Guofeng Quan and 4 more
Oct 5, 2026210 votesarXiv 2610.08448
Language
04
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
Deyuan Liu, Yihao Hu, Jingxuan Zhang and 13 more
Oct 6, 2026171 votesarXiv 2610.09823
Vision
05
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Team Kandinsky, Julia Agafonova, Bulat Akhmatov and 85 more
Oct 3, 2026169 votesarXiv 2610.05608
Vision
06
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi and 9 more
Oct 5, 2026165 votesarXiv 2610.08077
Reasoning and agents
07
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
Shaokun Zhang, Yifan Zhang, Jian Hu and 5 more
Oct 4, 2026148 votesarXiv 2610.06647
Language
08
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Yibo Li, Jinhang Qiu, Zhi Zheng and 4 more
Oct 7, 2026136 votesarXiv 2610.08215
Reasoning and agents
09
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Tianyu Fu, Tengxuan Liu, Ruoxi Wang and 4 more
Oct 7, 2026129 votesarXiv 2610.12242
Language
10
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
Bo Yin, Xiaobin Hu, Jiaqi Zhao and 1 more
Sep 29, 2026125 votesarXiv 2609.38839
Vision
11
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Bingchen Yao, Haobo Xu, Haokun Lin and 6 more
Sep 28, 2026122 votesarXiv 2609.38169
Language
12
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
Bingxuan Li, Siqi Song, Yizhuo Wu and 3 more
Sep 28, 2026114 votesarXiv 2609.38078
Robotics
13
Long-WAM: Scaling the Context of World-Action Models
Wei Huang, Bohan Zhang, Chenzhi Liu and 13 more
Oct 6, 2026106 votesarXiv 2610.10528
Robotics
14
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Quanyu Long, Xiao Chen, Jianda Chen and 4 more
Oct 4, 2026105 votesarXiv 2610.06100
Language
15
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Guangyi Liu, Yong Liu, Jiangning Zhang
Oct 5, 2026104 votesarXiv 2610.08699
Reasoning and agents

All papers

Loading the papers

Catalogue List

Titles, authors and dates come from arXiv. Vote counts come from the public Hugging Face Daily Papers list. Every paper belongs to its authors and opens on arXiv. Updated Oct 12, 2026.