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)

27,001 to 27,060 of 27,178

Decision-Support and Modeling with Large Language Models for Geothermal Well Arrays
Edwin Ouko, Emmanuel Lujan, Alan Edelman +1
cs.AIcs.CEarXiv:2608.22068v12026
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
Xiaogeng Liu, Nan Xu, Muhao Chen +1
cs.CLcs.AIarXiv:2310.04451v22023
CondConv: Conditionally Parameterized Convolutions for Efficient Inference
Brandon Yang, Gabriel Bender, Quoc V. Le +1
cs.CVcs.AIcs.LGarXiv:1904.04971v32019
Confident and Wrong: Silent Semantic Failures in Coding Agents
Aman Mehta
cs.SEcs.AIarXiv:2603.25764v32026
SWE-Universe: Scale Real-World Verifiable Environments to Millions
Mouxiang Chen, Lei Zhang, Yunlong Feng +15
cs.SEcs.AIarXiv:2602.02361v12026
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges
Zi-Han Wang, Lam Nguyen, Zhengyang Zhao +4
cs.AIcs.CLarXiv:2603.11863v22026
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
Dianyi Wang, Chaofan Ma, Feng Han +8
cs.CVcs.AIarXiv:2602.02437v42026
Understanding disentangling in $β$-VAE
Christopher P. Burgess, Irina Higgins, Arka Pal +4
stat.MLcs.AIcs.LGarXiv:1804.03599v12018
Experiential Reinforcement Learning
Taiwei Shi, Sihao Chen, Bowen Jiang +3
cs.LGcs.AIarXiv:2602.13949v12026
Learning to Continually Learn via Meta-learning Agentic Memory Designs
Yiming Xiong, Shengran Hu, Jeff Clune
cs.AIarXiv:2602.07755v12026
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Ziyin Zhang, Zihan Liao, Hang Yu +2
cs.CLcs.AIarXiv:2603.19223v12026
DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
Yang Zhou, Hao Shao, Letian Wang +3
cs.CVcs.AIcs.ROarXiv:2601.01528v22026
On Evaluation of Embodied Navigation Agents
Peter Anderson, Angel Chang, Devendra Singh Chaplot +8
cs.AIcs.CVcs.LGarXiv:1807.06757v12018
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
Qixing Zhou, Jiacheng Zhang, Haiyang Wang +9
cs.SEcs.AIarXiv:2602.10975v12026
Hyperagents
Jenny Zhang, Bingchen Zhao, Wannan Yang +5
cs.AIarXiv:2603.19461v12026
Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
Dongming Jiang, Yi Li, Songtao Wei +8
cs.CLcs.AIarXiv:2602.19320v22026
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Christopher Clark, Jieyu Zhang, Zixian Ma +18
cs.CVcs.AIarXiv:2601.10611v42026
DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
Yang Zhou, Xiaofeng Wang, Hao Shao +8
cs.CVcs.AIcs.ROarXiv:2604.01765v12026
An LLM agent for end-to-end computational materials discovery
Chen Yuntong, Huang Ju, Liu Yu +6
cond-mat.mtrl-scics.AIarXiv:2608.20434v12026
Universal statistical signatures of evolution in artificial intelligence architectures
Theodor Spiro
q-bio.PEcs.AIcs.CYarXiv:2604.10571v12026
General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
Junlin Liu, Shengnan An, Shuang Zhou +10
cs.CLcs.AIarXiv:2604.11778v12026
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
Yein Park, Jungwoo Park, Jaewoo Kang
cs.AIarXiv:2509.25843v22025
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
Mélanie Roschewitz, Kenneth Styppa, Yitian Tao +10
cs.AIarXiv:2604.15231v22026
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
Qifan Zhang, Dongyang Ma, Tianqing Fang +5
cs.AIarXiv:2604.18131v12026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3
cs.CRcs.AIarXiv:2604.17596v12026
EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
Xinyu Zhu, Yuzhu Cai, Zexi Liu +20
cs.AIarXiv:2604.17406v42026
MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
Szu-Chi Chen, I-Ning Tsai, Yi-Cheng Lin +2
cs.CLcs.AIcs.SDarXiv:2604.17435v12026
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Shaden Alshammari, Kevin Wen, Abrar Zainal +5
cs.AIcs.DLcs.IRarXiv:2604.18584v22026
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
Yusuf Çelebi, Yağız Asker, Özay Ezerceli +4
cs.LGcs.AIcs.CLarXiv:2604.19321v12026
Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization
Jiarui Yao, Ruida Wang, Hao Bai +1
cs.LGcs.AIcs.CLarXiv:2601.10201v22026
AI with Authority, from Application to Silicon
Jason Hickey
cs.SEcs.AIcs.ARarXiv:2608.21356v12026
Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness
Yu-Chao Huang, Haochen Zhang, Nicholas Konz +1
cs.LGcs.AIarXiv:2608.21207v12026
DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization
Naiyuan Li, Li Dong, Diqun Yan
cs.SDcs.AIarXiv:2608.21176v12026
Source-Free MT Evaluation Is Not MT Evaluation
Baban Gain, Ramakrishna Appicharla, Asif Ekbal
cs.CLcs.AIarXiv:2608.20925v12026
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
Carson Rodrigues, Oysturn Vas
cs.CLcs.AIarXiv:2608.20371v12026
Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
Wei Shao, Chongzhou Fang, Zuxiong Tan +4
cs.CRcs.AIarXiv:2608.20563v12026
Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
Rana Muhammad Usman, Dominic Williamson
physics.soc-phcs.AIcs.MAarXiv:2608.20438v12026
ProofJudge: Tool-Grounded LLM Evaluation of Formal Proof Quality in Mathlib
Shane Caldwell
cs.LOcs.AIcs.CLarXiv:2608.20432v12026
Can Legal AI Know When It Is Wrong? And Do Students Know When It Is?
Angel Mary John, Vipin Kumar Singh, Jerrin Thomas Panachakel
cs.AIarXiv:2608.21089v12026
When Vocabulary Comprehension Fails Clinical Reasoning: Evaluating Therapy Bots' Safety Risks for Generation Alpha
Manisha Mehta, Virendra Mehta
cs.CLcs.AIcs.CYarXiv:2608.20345v12026
Fine-Grain GPU Parallelization of the Generalized Partition Crossover for Large-Scale Traveling Salesman Problems
Swetha Varadarajan, Darrell Whitley
cs.AIcs.NEarXiv:2608.21233v12026
Ontology-supported AI Model and Dataset Management
Jan Novacek, Ali Ahari, Tobias Müller +3
cs.AIarXiv:2608.21224v12026
The Logic of Machine Self-Preservation
Cheng Siong Chin
cs.AIcs.CYcs.MAarXiv:2608.20940v12026
Lost in Translation: How Universal Ethical Values Fail to Translate Across Global Contexts
Ozioma C. Oguine, Munachimso B. Oguine, Cesar Cervera +6
cs.AIcs.HCarXiv:2608.20490v12026
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
Vu Hung Nguyen, Thanh Nguyen
cs.AIcs.SEarXiv:2608.20341v12026
Representation Affects Retrieval: A Case Study of Skill Discovery and Routing in a Multimodal Agent Harness
Kevin Dela Rosa
cs.AIarXiv:2608.20389v12026
Environmental Slow AI: Design Principles for Generative Systems
Vanessa Utz
cs.AIcs.CYarXiv:2608.20398v12026
A Minimalist Approach to Offline Reinforcement Learning
Scott Fujimoto, Shixiang Shane Gu
cs.LGcs.AIstat.MLarXiv:2106.06860v22021
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
Weiyu Sun, Liangliang Chen, Yongnuo Cai +3
cs.CVcs.AIcs.CYarXiv:2602.00095v32026
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo +1
cs.CVcs.AIcs.LGarXiv:2104.13921v32021
Taskonomy: Disentangling Task Transfer Learning
Amir Zamir, Alexander Sax, William Shen +3
cs.CVcs.AIcs.LGarXiv:1804.08328v12018
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Wenhu Chen, Xueguang Ma, Xinyi Wang +1
cs.CLcs.AIarXiv:2211.12588v42022
VideoBERT: A Joint Model for Video and Language Representation Learning
Chen Sun, Austin Myers, Carl Vondrick +2
cs.CVcs.AIarXiv:1904.01766v22019
Training Large Language Models to Predict Clinical Events
Benjamin Turtel, Paul Wilczewski, Kris Skotheim
cs.LGcs.AIcs.CLarXiv:2605.12817v12026
Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
Kush Juvekar, Kavya Manohar, Aditya Srinivas Menon +2
cs.CLcs.AIarXiv:2605.13087v22026
Large Language Models Are Human-Level Prompt Engineers
Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han +4
cs.LGcs.AIcs.CLarXiv:2211.01910v22022
Scientific reasoning does not reliably translate into scientific forecasting in frontier AI
Sean Wu, Pan Lu, Yupeng Chen +7
cs.AIarXiv:2605.22681v22026
Transformers in Time Series: A Survey
Qingsong Wen, Tian Zhou, Chaoli Zhang +4
cs.LGcs.AIeess.SParXiv:2202.07125v52022
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Dmitry Kalashnikov, Alex Irpan, Peter Pastor +8
cs.LGcs.AIcs.CVarXiv:1806.10293v32018
Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings
Stanislav Kirdey, Clark Labs Inc
cs.AIarXiv:2605.28034v12026

Artificial Intelligence

Decision-Support and Modeling with Large Language Models for Geothermal Well Arrays

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

CondConv: Conditionally Parameterized Convolutions for Efficient Inference

Confident and Wrong: Silent Semantic Failures in Coding Agents

SWE-Universe: Scale Real-World Verifiable Environments to Millions

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Understanding disentangling in $β$-VAE

Experiential Reinforcement Learning

Learning to Continually Learn via Meta-learning Agentic Memory Designs

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

On Evaluation of Embodied Navigation Agents

FeatureBench: Benchmarking Agentic Coding for Complex Feature Development

Hyperagents

Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

An LLM agent for end-to-end computational materials discovery

Universal statistical signatures of evolution in artificial intelligence architectures

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models

Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization

AI with Authority, from Application to Silicon

Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness

DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization

Source-Free MT Evaluation Is Not MT Evaluation

When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems

Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources

ProofJudge: Tool-Grounded LLM Evaluation of Formal Proof Quality in Mathlib

Can Legal AI Know When It Is Wrong? And Do Students Know When It Is?

When Vocabulary Comprehension Fails Clinical Reasoning: Evaluating Therapy Bots' Safety Risks for Generation Alpha

Fine-Grain GPU Parallelization of the Generalized Partition Crossover for Large-Scale Traveling Salesman Problems

Ontology-supported AI Model and Dataset Management

The Logic of Machine Self-Preservation

Lost in Translation: How Universal Ethical Values Fail to Translate Across Global Contexts

SDAD: Spec-Driven Agentic Development for the AI-Native SDLC

Representation Affects Retrieval: A Case Study of Skill Discovery and Routing in a Multimodal Agent Harness

Environmental Slow AI: Design Principles for Generative Systems

A Minimalist Approach to Offline Reinforcement Learning

EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

Taskonomy: Disentangling Task Transfer Learning

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

VideoBERT: A Joint Model for Video and Language Representation Learning

Training Large Language Models to Predict Clinical Events

Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

Large Language Models Are Human-Level Prompt Engineers

Scientific reasoning does not reliably translate into scientific forecasting in frontier AI

Transformers in Time Series: A Survey

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings