The Research Desk.

The most upvoted and starred AI research crossing the community today.

Last Brew Time: Aug 13, 2026, 11:04 AM PT

X.com Research Buzz

Retrieval
The Tragedy of the Cognitive Commons: How AI Could Disrupt the Regeneration of Professional Expertise
X.com
15970

The Tragedy of the Cognitive Commons: How AI Could Disrupt the Regeneration of Professional Expertise

Nolan Lovett

NLP
Emergent Introspective Awareness in Large Language Models
X.com
5935

Emergent Introspective Awareness in Large Language Models

Jack Lindsey

Anthropic

Reinforcement Learning
Modeling Earth-Scale Human-Like Societies with One Billion Agents
X.com
4906

Modeling Earth-Scale Human-Like Societies with One Billion Agents

Haoxiang Guan, Jiyan He, Liyang Fan, Zhenzhen Ren, Shaobin He, Xin Yu, Yuan Chen, Xueyin Xu, Shuxin Zheng, Yan Gao, Enhong Chen, Tie-Yan Liu, Zhen Liu

AlphaXiv Trending

NLP
Stealing Reasoning Traces from Proprietary LLM APIs
AlphaXiv
273

Stealing Reasoning Traces from Proprietary LLM APIs

Alexander Panfilov, David Schmotz, Ilia Shumailov

Affiliation: ELLIS Institute Tübingen, Affiliation: Max Planck Institute for Intelligent Systems, Affiliation: ELLIS Institute Tübingen Affiliation: Max Planck Institute for Intelligent Systems, ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems

Reasoning
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
AlphaXiv
254

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Björn Engdahl, Adrian Kosowski, Jan Chorowski

Affiliation: Pathway, https://pathway.com/research, Affiliation: New York University, https://pathway.com/research, New York University

Computer Vision
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
AlphaXiv
68

JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

Yihan Lin, Jiawei He, Shifeng Bao

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
AlphaXiv
47

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Vin Bo, Asher Cai

Mind Lab

Reinforcement Learning
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
AlphaXiv
38

Mismatch Matters: On-Policy Distillation Beyond Token Agreement

Zichao Yu, Chengzhi Yu, Shengze Xu

Affiliation: The Chinese University of Hong Kong, The Chinese University of Hong Kong, The University of Hong Kong University of Science and Technology of China

Reinforcement Learning
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
AlphaXiv
37

Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

Kushal Chakrabarti

HuggingFace Daily Papers

Reinforcement Learning
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
HuggingFace
72

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan

Zjunlp
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
HuggingFace
72

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu

ZJUNLP

Reinforcement Learning
Self-Evolving Embodied Agents via Skill-Harness Evolution
HuggingFace
9

Self-Evolving Embodied Agents via Skill-Harness Evolution

Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang

Insait Institute
Parameter Exploration for RLVR via Variational Learning
HuggingFace
2

Parameter Exploration for RLVR via Variational Learning

Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych

BayesRL

NLP
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
HuggingFace
2

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop

Igor Itkin

NLP
Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
HuggingFace
1

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

Josef Liyanjun Chen