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)

4,021 to 4,080 of 15,235

Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
Vennise Ho, Kristian Diana, Sandy Mourad +3
cs.AIcs.LGarXiv:2608.28944v12026
Removing RLHF Protections in GPT-4 via Fine-Tuning
Qiusi Zhan, Richard Fang, Rohan Bindu +3
cs.CLcs.AIarXiv:2311.05553v32023
Robin: A multi-agent system for automating scientific discovery
Ali Essam Ghareeb, Benjamin Chang, Ludovico Mitchener +7
cs.AIcs.MAq-bio.QMarXiv:2505.13400v12025
Linear Mode Connectivity in Multitask and Continual Learning
Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur +2
cs.LGcs.AIcs.CVarXiv:2010.04495v12020
AOI-Net: Structural Face AOI-Guided Eye-Gaze Track Representation Learning for Autism Spectrum Disorder Detection
Zhanpei Huang, Binbin Sun, Jialiang Chen +5
cs.CVcs.AIcs.ETarXiv:2608.29289v12026
OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization
Yishan Yao, Binjun Li, Hanling Yi +5
cs.CLcs.AIcs.LGarXiv:2609.00066v12026
Unsupervised Diverse Colorization via Generative Adversarial Networks
Yun Cao, Zhiming Zhou, Weinan Zhang +1
cs.CVcs.AIarXiv:1702.06674v22017
Doc-to-LoRA: Learning to Instantly Internalize Contexts
Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka +1
cs.CLcs.AIarXiv:2602.15902v12026
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
Zhibin Lan, Liqiang Niu, Fandong Meng +2
cs.CVcs.AIcs.CLarXiv:2503.04812v22025
Getting pwn'd by AI: Penetration Testing with Large Language Models
Andreas Happe, Jürgen Cito
cs.CLcs.AIcs.CRarXiv:2308.00121v32023
ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
Bufang Yang, Lilin Xu, Liekang Zeng +7
cs.AIcs.CLcs.HCarXiv:2505.14668v22025
Test-time regression: a unifying framework for designing sequence models with associative memory
Ke Alexander Wang, Jiaxin Shi, Emily B. Fox
cs.LGcs.AIcs.NEarXiv:2501.12352v32025
DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering
Zihan Huang, Shihang Wu, Junle Liu +4
cs.CVcs.AIarXiv:2608.29037v12026
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
Pritam Dash, Tongyu Ge, Aditi Jain +2
cs.CRcs.AIarXiv:2606.04329v22026
TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms
Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri +5
cs.DCcs.AIarXiv:2501.02600v12025
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
Minkyu Kim, Juhwan Choi, YoungBin Kim
cs.AIarXiv:2608.29589v12026
Meta Context Engineering via Agentic Skill Evolution
Haoran Ye, Xuning He, Vincent Arak +2
cs.AIcs.NEarXiv:2601.21557v22026
Large Language Models to Enhance Bayesian Optimization
Tennison Liu, Nicolás Astorga, Nabeel Seedat +1
cs.LGcs.AIarXiv:2402.03921v22024
PyVision: Agentic Vision with Dynamic Tooling
Shitian Zhao, Haoquan Zhang, Shaoheng Lin +4
cs.CLcs.AIcs.CVarXiv:2507.07998v32025
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang +26
cs.CRcs.AIarXiv:2601.04603v12026
UserBench: An Interactive Gym Environment for User-Centric Agents
Cheng Qian, Zuxin Liu, Akshara Prabhakar +9
cs.AIcs.CLcs.LGarXiv:2507.22034v12025
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
Zhanming Shen, Jintao Tong, Shaotian Yan +9
cs.AIcs.LGarXiv:2607.02234v12026
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Andy Zhou, Bo Li, Haohan Wang
cs.LGcs.AIcs.CLarXiv:2401.17263v52024
CineForge: Self-Improving Agents for Long-Horizon Video Generation
Junxiang Liu, Lin Wang, Haiyu Shi +10
cs.CVcs.AIarXiv:2608.29621v12026
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Chengshuai Zhao, Zhen Tan, Pingchuan Ma +5
cs.AIcs.CLcs.LGarXiv:2508.01191v62025
Steering Large Language Model Activations in Sparse Spaces
Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki +2
cs.LGcs.AIarXiv:2503.00177v12025
Internet of Agents: Fundamentals, Applications, and Challenges
Yuntao Wang, Shaolong Guo, Yanghe Pan +6
cs.MAcs.AIarXiv:2505.07176v22025
Generative Judge for Evaluating Alignment
Junlong Li, Shichao Sun, Weizhe Yuan +3
cs.CLcs.AIarXiv:2310.05470v22023
Lifelong Learning of Large Language Model based Agents: A Roadmap
Junhao Zheng, Chengming Shi, Xidi Cai +5
cs.AIarXiv:2501.07278v22025
Contrastive Code Representation Learning
Paras Jain, Ajay Jain, Tianjun Zhang +3
cs.LGcs.AIcs.PLarXiv:2007.04973v42020
Safety Guardrails for LLM-Enabled Robots
Zachary Ravichandran, Alexander Robey, Vijay Kumar +2
cs.ROcs.AIarXiv:2503.07885v22025
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
Hsin-Yuan Huang, Chenguang Zhu, Yelong Shen +1
cs.CLcs.AIarXiv:1711.07341v22017
EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation
Sihang Jia, Shuliang Liu, Songbo Yang +1
cs.AIcs.CVarXiv:2608.29092v12026
Steer LLM Latents for Hallucination Detection
Seongheon Park, Xuefeng Du, Min-Hsuan Yeh +2
cs.LGcs.AIcs.CLarXiv:2503.01917v22025
A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'
Ali Borji
cs.LGcs.AIarXiv:2410.12954v22024
On a Class of Bias-Amplifying Variables that Endanger Effect Estimates
Judea Pearl
stat.MEcs.AIarXiv:1203.3503v12012
Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
Xinyuan Gui, Shaowen Wang, Sheng Sun +3
cs.AIarXiv:2608.28726v12026
"Humans welcome to observe": A First Look at the Agent Social Network Moltbook
Yukun Jiang, Yage Zhang, Xinyue Shen +2
cs.SIcs.AIcs.CRarXiv:2602.10127v12026
RACER: Reinforced Agent Collaboration for Explainable Reasoning on Knowledge Graphs
Yuwei Lou, Hao Hu, Yuzhou Jiang +5
cs.AIarXiv:2608.29263v12026
Decoupling the Depth and Scope of Graph Neural Networks
Hanqing Zeng, Muhan Zhang, Yinglong Xia +6
cs.LGcs.AIarXiv:2201.07858v12022
Benevolent Bias in Multi-Turn Human-Agent Dialogue
Qianqi Liu, Jin Huang, Fethiye Irmak Dogan +1
cs.AIarXiv:2608.29206v12026
Fast Training of Diffusion Models with Masked Transformers
Hongkai Zheng, Weili Nie, Arash Vahdat +1
cs.CVcs.AIcs.LGarXiv:2306.09305v22023
Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
Kunvar Thaman
cs.LGcs.AIarXiv:2605.02964v12026
Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
Ke Yan, Lu Kou, David Zhang
cs.CVcs.AIcs.LGarXiv:1603.04535v22016
GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
Ye Yuan, Umar Iqbal, Pavlo Molchanov +2
cs.CVcs.AIcs.GRarXiv:2112.01524v22021
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov
cs.LGcs.AIcs.ROarXiv:2110.05038v32021
The Leaderboard Illusion
Shivalika Singh, Yiyang Nan, Alex Wang +10
cs.AIcs.CLcs.LGarXiv:2504.20879v22025
CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation
Peter Jansen, Oyvind Tafjord, Marissa Radensky +6
cs.AIcs.CLarXiv:2503.22708v12025
Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
Yiming Wang, Pei Zhang, Siyuan Huang +4
cs.CLcs.AIarXiv:2503.01422v32025
ASER: A Large-scale Eventuality Knowledge Graph
Hongming Zhang, Xin Liu, Haojie Pan +2
cs.AIcs.CLarXiv:1905.00270v32019
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Vijay Ekambaram, Arindam Jati, Pankaj Dayama +5
cs.LGcs.AIarXiv:2401.03955v82024
Deep Multimodal Subspace Clustering Networks
Mahdi Abavisani, Vishal M. Patel
cs.LGcs.AIcs.CVarXiv:1804.06498v32018
MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
Jia Xu, Tianyi Wei, Bojian Hou +7
cs.LGcs.AIcs.CLarXiv:2503.13509v22025
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Anthony +7
cs.LGcs.AIarXiv:2508.06601v22025
OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
Hongliang Lu, Zhonglin Xie, Yaoyu Wu +3
cs.AIcs.LGarXiv:2502.11102v22025
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
Leon Staufer, Kevin Feng, Kevin Wei +6
cs.CYcs.AIarXiv:2602.17753v22026
A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives
Weiqiang Jin, Hongyang Du, Shixiang Tang +2
cs.MAcs.AIarXiv:2503.13415v22025
When Do Larger Batches Help Scale LLM Reinforcement Learning?
Ziniu Li, Jinbo Wang, Guanhua Huang +3
cs.LGcs.AIarXiv:2608.29296v12026
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani +5
cs.CLcs.AIcs.IRarXiv:2502.08826v32025
It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
Ali Behrouz, Meisam Razaviyayn, Peilin Zhong +1
cs.LGcs.AIarXiv:2504.13173v12025

Artificial Intelligence

Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis

Removing RLHF Protections in GPT-4 via Fine-Tuning

Robin: A multi-agent system for automating scientific discovery

Linear Mode Connectivity in Multitask and Continual Learning

AOI-Net: Structural Face AOI-Guided Eye-Gaze Track Representation Learning for Autism Spectrum Disorder Detection

OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization

Unsupervised Diverse Colorization via Generative Adversarial Networks

Doc-to-LoRA: Learning to Instantly Internalize Contexts

LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning

Getting pwn'd by AI: Penetration Testing with Large Language Models

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

Test-time regression: a unifying framework for designing sequence models with associative memory

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines

Meta Context Engineering via Agentic Skill Evolution

Large Language Models to Enhance Bayesian Optimization

PyVision: Agentic Vision with Dynamic Tooling

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

UserBench: An Interactive Gym Environment for User-Centric Agents

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

CineForge: Self-Improving Agents for Long-Horizon Video Generation

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Steering Large Language Model Activations in Sparse Spaces

Internet of Agents: Fundamentals, Applications, and Challenges

Generative Judge for Evaluating Alignment

Lifelong Learning of Large Language Model based Agents: A Roadmap

Contrastive Code Representation Learning

Safety Guardrails for LLM-Enabled Robots

FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension

EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation

Steer LLM Latents for Hallucination Detection

A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'

On a Class of Bias-Amplifying Variables that Endanger Effect Estimates

Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference

"Humans welcome to observe": A First Look at the Agent Social Network Moltbook

RACER: Reinforced Agent Collaboration for Explainable Reasoning on Knowledge Graphs

Decoupling the Depth and Scope of Graph Neural Networks

Benevolent Bias in Multi-Turn Human-Agent Dialogue

Fast Training of Diffusion Models with Masked Transformers

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

Learning Domain-Invariant Subspace using Domain Features and Independence Maximization

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

The Leaderboard Illusion

CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

ASER: A Large-scale Eventuality Knowledge Graph

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series

Deep Multimodal Subspace Clustering Networks

MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems

A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives

When Do Larger Batches Help Scale LLM Reinforcement Learning?

Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization