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)

4,861 to 4,920 of 15,259

Kosmos: An AI Scientist for Autonomous Discovery
Ludovico Mitchener, Angela Yiu, Benjamin Chang +34
cs.AIarXiv:2511.02824v22025
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Jungseob Lee, Seongtae Hong, Dongyub Jude Lee +4
cs.AIcs.CLcs.CVarXiv:2609.00355v12026
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes
Jon Donnelly, Alina Jade Barnett, Chaofan Chen
cs.CVcs.AIcs.LGarXiv:2111.15000v32021
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
Dongya Jia, Zhuo Chen, Jiawei Chen +8
eess.AScs.AIcs.CLarXiv:2502.03930v42025
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
Chenwei Lou, Zewei Sun, Xinnian Liang +6
cs.LGcs.AIarXiv:2505.11896v22025
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
Weizhen Li, Jianbo Lin, Zhuosong Jiang +27
cs.AIcs.CLarXiv:2508.13167v12025
SafeArena: Evaluating the Safety of Autonomous Web Agents
Ada Defne Tur, Nicholas Meade, Xing Han Lù +6
cs.LGcs.AIcs.CLarXiv:2503.04957v12025
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
DiJia Su, Hanlin Zhu, Yingchen Xu +3
cs.CLcs.AIcs.LGarXiv:2502.03275v22025
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
Mert Cemri, Shubham Agrawal, Akshat Gupta +9
cs.NEcs.AIcs.CLarXiv:2602.20133v12026
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
Fuxiao Liu, Xiaoyang Wang, Wenlin Yao +5
cs.CLcs.AIarXiv:2311.10774v22023
SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
Minghan Chen, Guikun Chen, Wenguan Wang +1
cs.AIarXiv:2505.12346v12025
S*: Test Time Scaling for Code Generation
Dacheng Li, Shiyi Cao, Chengkun Cao +6
cs.LGcs.AIarXiv:2502.14382v12025
BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
Huayi Wang, Zirui Wang, Junli Ren +4
cs.ROcs.AIcs.LGarXiv:2502.10363v32025
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Qingkai Fang, Yan Zhou, Shoutao Guo +2
cs.CLcs.AIcs.SDarXiv:2505.02625v12025
Reinforcement Learning for Long-Horizon Interactive LLM Agents
Kevin Chen, Marco Cusumano-Towner, Brody Huval +4
cs.LGcs.AIarXiv:2502.01600v32025
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
Chaoqi Wang, Yibo Jiang, Chenghao Yang +2
cs.LGcs.AIstat.MLarXiv:2309.16240v12023
AgentEvolver: Towards Efficient Self-Evolving Agent System
Yunpeng Zhai, Shuchang Tao, Cheng Chen +10
cs.LGcs.AIcs.CLarXiv:2511.10395v12025
Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey
Yiwen Xu, Tariq M. Khan, Yang Song +1
cs.CVcs.AIarXiv:2605.06714v12026
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
Weidi Luo, Shenghong Dai, Xiaogeng Liu +4
cs.AIarXiv:2502.11448v22025
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Han Zhou, Xingchen Wan, Ruoxi Sun +5
cs.LGcs.AIcs.CLarXiv:2502.02533v22025
Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals
Andrew Cotter, Heinrich Jiang, Serena Wang +4
cs.LGcs.AIcs.GTarXiv:1809.04198v12018
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Deepak Nathani, Lovish Madaan, Nicholas Roberts +14
cs.CLcs.AIcs.LGarXiv:2502.14499v12025
Tree Search for LLM Agent Reinforcement Learning
Yuxiang Ji, Ziyu Ma, Yong Wang +3
cs.LGcs.AIarXiv:2509.21240v32025
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
Tom Wollschläger, Jannes Elstner, Simon Geisler +3
cs.LGcs.AIcs.CLarXiv:2502.17420v22025
Memp: Exploring Agent Procedural Memory
Runnan Fang, Yuan Liang, Xiaobin Wang +6
cs.CLcs.AIcs.LGarXiv:2508.06433v42025
Diffusion Beats Autoregressive in Data-Constrained Settings
Mihir Prabhudesai, Mengning Wu, Amir Zadeh +2
cs.LGcs.AIcs.CVarXiv:2507.15857v72025
DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark
Jayanta Sadhu, Sayem Shahad, Kenneth Marino
cs.AIarXiv:2608.30413v12026
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Vighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum +3
cs.CLcs.AIcs.LGarXiv:2501.05707v22025
TraveL: Transformer-based Multi-view Path Distributional Representation Learning
Fang He, Tao-yang Fu, Wang-chien Lee
cs.LGcs.AIarXiv:2609.03427v12026
Evolutionary bagging for ensemble learning
Giang Ngo, Rodney Beard, Rohitash Chandra
cs.NEcs.AIarXiv:2208.02400v32022
The Curious Robot: Learning Visual Representations via Physical Interactions
Lerrel Pinto, Dhiraj Gandhi, Yuanfeng Han +2
cs.CVcs.AIcs.ROarXiv:1604.01360v22016
Innovation networks
Petra Ahrweiler, Mark T. Keane
cs.AIcs.SIphysics.soc-pharXiv:1308.2234v12013
Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo +4
cs.CVcs.AIcs.CLarXiv:2505.18079v42025
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
Wenkai Yang, Shuming Ma, Yankai Lin +1
cs.CLcs.AIarXiv:2502.18080v22025
ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation
Muzhao Tian, Zezi Zeng, Yifan Yang +14
cs.AIarXiv:2609.00194v12026
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
Xingran Chen, Rohit Bhagat, Ghadir Ayache +3
cs.LGcs.AIarXiv:2609.00078v12026
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
Sayash Kapoor, Benedikt Stroebl, Peter Kirgis +28
cs.AIcs.CLarXiv:2510.11977v12025
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
Zhihang Lin, Mingbao Lin, Yuan Xie +1
cs.AIarXiv:2503.22342v22025
LLM Generated Persona is a Promise with a Catch
Ang Li, Haozhe Chen, Hongseok Namkoong +1
cs.CLcs.AIcs.CYarXiv:2503.16527v12025
Yume: An Interactive World Generation Model
Xiaofeng Mao, Shaoheng Lin, Zhen Li +7
cs.CVcs.AIcs.HCarXiv:2507.17744v12025
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes
Guanghui Lan
cs.LGcs.AImath.OCarXiv:2102.00135v62021
MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
Yannis Katsis, Sara Rosenthal, Kshitij Fadnis +7
cs.CLcs.AIarXiv:2501.03468v12025
Convergent Linear Representations of Emergent Misalignment
Anna Soligo, Edward Turner, Senthooran Rajamanoharan +1
cs.LGcs.AIarXiv:2506.11618v22025
SAFE: Multitask Failure Detection for Vision-Language-Action Models
Qiao Gu, Yuanliang Ju, Shengxiang Sun +4
cs.ROcs.AIarXiv:2506.09937v22025
Flawed in Nature, Perfect through Evolution
J. M. Diederik Kruijssen
cs.LGcs.AIcs.NEarXiv:2609.00129v12026
Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
Junde Wu, Jiayuan Zhu, Yuyuan Liu +2
cs.AIcs.CLarXiv:2502.04644v22025
Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
Qixiu Li, Yu Deng, Yaobo Liang +14
cs.ROcs.AIcs.CVarXiv:2510.21571v12025
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
Kai Liu, Wei Li, Lai Chen +8
cs.CVcs.AIcs.SDarXiv:2503.23377v22025
On Synthesis of Metric Interval Temporal Logics
Hsi-Ming Ho, Shankaranarayanan Krishna, Khushraj Madnani
cs.LOcs.AIarXiv:2609.01032v12026
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
Junliang Guo, Yang Ye, Tianyu He +4
cs.CVcs.AIarXiv:2504.08388v12025
LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving
Zhijie Qiao, Haowei Li, Zhong Cao +1
cs.ROcs.AIarXiv:2505.00284v32025
The Transformative Potential of Artificial Intelligence
Ross Gruetzemacher, Jess Whittlestone
cs.CYcs.AIarXiv:1912.00747v32019
Darknet and Deepnet Mining for Proactive Cybersecurity Threat Intelligence
Eric Nunes, Ahmad Diab, Andrew Gunn +7
cs.CRcs.AIcs.CYarXiv:1607.08583v12016
Persona Features Control Emergent Misalignment
Miles Wang, Tom Dupré la Tour, Olivia Watkins +8
cs.LGcs.AIarXiv:2506.19823v22025
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Keming Wu, Sicong Jiang, Max Ku +3
cs.CVcs.AIcs.CLarXiv:2509.26346v22025
RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection
Quan Hao, Chenxi Zhang, Ziyang Tao +6
cs.CVcs.AIarXiv:2608.30709v12026
General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms
Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa +3
cs.AIarXiv:1802.10363v42018
Artificial Intelligence in the Battle against Coronavirus (COVID-19): A Survey and Future Research Directions
Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Dung Tien Nguyen +7
cs.CYcs.AIcs.LGarXiv:2008.07343v42020
AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents
Hanjun Luo, Shenyu Dai, Chiming Ni +5
cs.AIarXiv:2506.00641v32025
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross, Arnaud Gotlieb
cs.SEcs.AIarXiv:2609.00838v12026

Artificial Intelligence

Kosmos: An AI Scientist for Autonomous Discovery

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

SafeArena: Evaluating the Safety of Autonomous Web Agents

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization

MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

S*: Test Time Scaling for Code Generation

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Reinforcement Learning for Long-Horizon Interactive LLM Agents

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

AgentEvolver: Towards Efficient Self-Evolving Agent System

Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Tree Search for LLM Agent Reinforcement Learning

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

Memp: Exploring Agent Procedural Memory

Diffusion Beats Autoregressive in Data-Constrained Settings

DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

TraveL: Transformer-based Multi-view Path Distributional Representation Learning

Evolutionary bagging for ensemble learning

The Curious Robot: Learning Visual Representations via Physical Interactions

Innovation networks

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning

ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation

RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

LLM Generated Persona is a Promise with a Catch

Yume: An Interactive World Generation Model

Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes

MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems

Convergent Linear Representations of Emergent Misalignment

SAFE: Multitask Failure Detection for Vision-Language-Action Models

Flawed in Nature, Perfect through Evolution

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization

On Synthesis of Metric Interval Temporal Logics

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving

The Transformative Potential of Artificial Intelligence

Darknet and Deepnet Mining for Proactive Cybersecurity Threat Intelligence

Persona Features Control Emergent Misalignment

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection

General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms

Artificial Intelligence in the Battle against Coronavirus (COVID-19): A Survey and Future Research Directions

AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents

Probabilistic Model Checking of Autoregressive Neural Sequence Models