Artificial Intelligence

Papers filed under cs.AI on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

12,001 to 12,060 of 15,291

Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction
Jun Hou, Yi Fang, Xuan Wang
cs.AIcs.LGarXiv:2608.22176v12026
Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
Daniel Hennes, Zun Li, John Schultz +1
cs.GTcs.AIcs.LGarXiv:2603.10098v12026
MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning
Ziyang Luo, Yan Yang, Xiangru Jian +5
cs.AIcs.LGarXiv:2608.22167v12026
Small Language Model enabled Autonomous agent for Language-Conditioned Cognitive Radar
Minhaj Uddin Ahmad, Zakia Zaman, Shunqiao Sun +1
eess.SPcs.AIeess.SYarXiv:2608.11596v12026
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
Chen Yang, Guangyue Peng, Jiaying Zhu +12
cs.AIcs.CLarXiv:2602.13367v12026
Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning
Zhaoda Du, Qiaojie Zheng, Xiaoli Zhang
cs.AIarXiv:2608.22128v12026
Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems
Henry Fordjour Ansah, Shreya Banerjee, Pranish Ghimire
cs.AIarXiv:2608.22143v12026
Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification
Qian Ma, Anna Squicciarini, Sarah Rajtmajer
cs.AIcs.CLarXiv:2608.22161v12026
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments
Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan +2
cs.LGcs.AIcs.CVarXiv:2601.01075v22026
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
Michael Niemeyer, Jonathan T. Barron, Ben Mildenhall +3
cs.CVcs.AIcs.GRarXiv:2112.00724v12021
BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
cs.AIarXiv:2602.12876v22026
Vega: Learning to Drive with Natural Language Instructions
Sicheng Zuo, Yuxuan Li, Wenzhao Zheng +3
cs.CVcs.AIcs.ROarXiv:2603.25741v22026
GISA: A Benchmark for General Information-Seeking Assistant
Yutao Zhu, Xingshuo Zhang, Maosen Zhang +9
cs.CLcs.AIcs.IRarXiv:2602.08543v22026
Mixture-of-Experts with Expert Choice Routing
Yanqi Zhou, Tao Lei, Hanxiao Liu +7
cs.LGcs.AIarXiv:2202.09368v22022
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
Sein Kim, Sangwu Park, Hongseok Kang +6
cs.IRcs.AIarXiv:2602.12612v22026
NExT-GPT: Any-to-Any Multimodal LLM
Shengqiong Wu, Hao Fei, Leigang Qu +2
cs.AIcs.CLcs.LGarXiv:2309.05519v32023
AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems
Zhixu Du, Yiran Chen
cs.AIarXiv:2608.22160v12026
The many Shapley values for model explanation
Mukund Sundararajan, Amir Najmi
cs.AIcs.LGecon.THarXiv:1908.08474v22019
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
Zanlin Ni, Shenzhi Wang, Yang Yue +8
cs.CLcs.AIcs.LGarXiv:2601.15165v42026
Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations
Samira Golsefid
cs.AIcs.CLarXiv:2608.22138v12026
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
Xiaoyuan Liu, Tian Liang, Dongyang Ma +4
cs.AIarXiv:2602.12108v12026
MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data
Xinyuan Song, Bowen Zhu, Hasibul Haque +1
cs.AIarXiv:2608.22141v12026
MegaMem: A Retrieval Solution for Ultra-Large Context Windows
Xinyuan Song, Bowen Zhu, Hasibul Haque +1
cs.AIarXiv:2608.22137v12026
Solving math word problems with process- and outcome-based feedback
Jonathan Uesato, Nate Kushman, Ramana Kumar +6
cs.LGcs.AIcs.CLarXiv:2211.14275v12022
Zero-Shot Relation Extraction via Reading Comprehension
Omer Levy, Minjoon Seo, Eunsol Choi +1
cs.CLcs.AIcs.LGarXiv:1706.04115v12017
Counterfactual Reasoning and Learning Systems
Léon Bottou, Jonas Peters, Joaquin Quiñonero-Candela +6
cs.LGcs.AIcs.IRarXiv:1209.2355v52012
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Xingjun Ma, Yixu Wang, Hengyuan Xu +18
cs.AIcs.CLcs.CVarXiv:2601.10527v22026
Prompt Injection attack against LLM-integrated Applications
Yi Liu, Gelei Deng, Yuekang Li +9
cs.CRcs.AIcs.CLarXiv:2306.05499v32023
TranslateGemma Technical Report
Mara Finkelstein, Isaac Caswell, Tobias Domhan +18
cs.CLcs.AIarXiv:2601.09012v32026
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Haoyu Lu, Wen Liu, Bo Zhang +12
cs.AIarXiv:2403.05525v22024
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
Han Wang, Yifan Sun, Brian Ko +8
cs.AIarXiv:2603.28590v32026
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin +5
cs.LGcs.AIcs.CVarXiv:2603.24440v12026
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Deep Ganguli, Liane Lovitt, Jackson Kernion +33
cs.CLcs.AIcs.CYarXiv:2209.07858v22022
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
Mohit Shridhar, Lucas Manuelli, Dieter Fox
cs.ROcs.AIcs.CLarXiv:2209.05451v22022
TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts
Yu Xu, Hongbin Yan, Juan Cao +11
cs.CVcs.AIarXiv:2601.08881v22026
DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction
Jiayang Shi, Daniel M. Pelt, K. Joost Batenburg
eess.IVcs.AIcs.CVarXiv:2602.18589v12026
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
Zhang Li, Zhibo Lin, Qiang Liu +7
cs.CVcs.AIarXiv:2603.28130v12026
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Fangda Ye, Yuxin Hu, Pengxiang Zhu +19
cs.AIcs.CLarXiv:2603.28407v12026
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Andreas Steiner, Alexander Kolesnikov, Xiaohua Zhai +3
cs.CVcs.AIcs.LGarXiv:2106.10270v22021
MolmoPoint: Better Pointing for VLMs with Grounding Tokens
Christopher Clark, Yue Yang, Jae Sung Park +8
cs.CVcs.AIarXiv:2603.28069v12026
Towards a Medical AI Scientist
Hongtao Wu, Boyun Zheng, Dingjie Song +5
cs.AIcs.LGarXiv:2603.28589v12026
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Jiayuan Mao, Chuang Gan, Pushmeet Kohli +2
cs.CVcs.AIcs.CLarXiv:1904.12584v12019
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
Xinyu Jia, Chuang Zhu, Minzhen Li +3
cs.CVcs.AIarXiv:2108.10831v42021
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh +2
cs.LGcs.AIcs.IRarXiv:1602.05352v22016
SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
Tim Baumgärtner, Iryna Gurevych
cs.CLcs.AIarXiv:2601.12910v32026
MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
Ning Ding, Fangcheng Liu, Kyungrae Kim +4
cs.LGcs.AIcs.CLarXiv:2602.03359v12026
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Bin Dou, Junru Zhang, Zhaoyi Yuan +6
cs.IRcs.AIarXiv:2608.23392v12026
Matching the Blanks: Distributional Similarity for Relation Learning
Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling +1
cs.CLcs.AIarXiv:1906.03158v12019
Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing
Zhaotian Weng, Antonis Antoniades, Deepak Nathani +3
cs.AIarXiv:2602.04837v12026
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Michael M. Bronstein, Joan Bruna, Taco Cohen +1
cs.LGcs.AIcs.CGarXiv:2104.13478v22021
APTER: Adaptive Post-Training with Expert-Grounded Rubrics
Xukai Wang, Liangqi Li, Zhiyue Xu +6
cs.AIarXiv:2608.14212v12026
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
Wuyang Li, Yang Gao, Mariam Hassan +4
cs.CVcs.AIarXiv:2605.15042v12026
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Haoran Tang, Rein Houthooft, Davis Foote +6
cs.AIcs.LGarXiv:1611.04717v32016
Learning to Retrieve from Agent Trajectories
Yuqi Zhou, Sunhao Dai, Changle Qu +3
cs.IRcs.AIcs.CLarXiv:2604.04949v12026
MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds
Minjae Seo, Wonwoo Choi, Geonwoo Han +7
cs.AIcs.CYarXiv:2608.22061v12026
Behavior Regularized Offline Reinforcement Learning
Yifan Wu, George Tucker, Ofir Nachum
cs.LGcs.AIstat.MLarXiv:1911.11361v12019
Computer Environments Elicit General Agentic Intelligence in LLMs
Daixuan Cheng, Shaohan Huang, Yuxian Gu +6
cs.CLcs.AIarXiv:2601.16206v32026
Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks
Amit Roth, Ivan Bercovich, Yonathan Efroni
cs.AIarXiv:2608.22103v12026
On a Formal Model of Safe and Scalable Self-driving Cars
Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua
cs.ROcs.AIstat.MLarXiv:1708.06374v62017
StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
Suraj Ranganath, Atharv Ramesh
cs.LGcs.AIcs.CRarXiv:2602.08934v22026

Artificial Intelligence

Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning

Small Language Model enabled Autonomous agent for Language-Conditioned Cognitive Radar

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning

Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems

Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

Vega: Learning to Drive with Natural Language Instructions

GISA: A Benchmark for General Information-Seeking Assistant

Mixture-of-Experts with Expert Choice Routing

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

NExT-GPT: Any-to-Any Multimodal LLM

AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems

The many Shapley values for model explanation

The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations

The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context

MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data

MegaMem: A Retrieval Solution for Ultra-Large Context Windows

Solving math word problems with process- and outcome-based feedback

Zero-Shot Relation Extraction via Reading Comprehension

Counterfactual Reasoning and Learning Systems

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5

Prompt Injection attack against LLM-integrated Applications

TranslateGemma Technical Report

DeepSeek-VL: Towards Real-World Vision-Language Understanding

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

MolmoPoint: Better Pointing for VLMs with Grounding Tokens

Towards a Medical AI Scientist

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

Recommendations as Treatments: Debiasing Learning and Evaluation

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling

Towards a Densing Law for User Representation Learning at Billion-Scale Capacity

Matching the Blanks: Distributional Similarity for Relation Learning

Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

APTER: Adaptive Post-Training with Expert-Grounded Rubrics

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Learning to Retrieve from Agent Trajectories

MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds

Behavior Regularized Offline Reinforcement Learning

Computer Environments Elicit General Agentic Intelligence in LLMs

Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks

On a Formal Model of Safe and Scalable Self-driving Cars

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors