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)

61 to 120 of 15,189

NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment
Wenqing Wu, Yi Zhao, Yuzhuo Wang +4
cs.CLcs.AIcs.DLarXiv:2604.11543v12026
Trustworthy AI: From Principles to Practices
Bo Li, Peng Qi, Bo Liu +5
cs.AIcs.LGarXiv:2110.01167v22021
Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions
Jiayi Bi, Yanjie Gao, Yuanmin Xie +4
cs.AIarXiv:2609.02371v12026
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
Hao Yin, Guangzong Si, Zilei Wang
cs.CVcs.AIarXiv:2503.13107v22025
Log-based Anomaly Detection Without Log Parsing
Van-Hoang Le, Hongyu Zhang
cs.SEcs.AIarXiv:2108.01955v32021
Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Dawei Liu, Zongxia Li, Hongyang Du +4
cs.AIarXiv:2604.05333v32026
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Hanchen Li, Runyuan He, Qizheng Zhang +11
cs.AIcs.CLcs.LGarXiv:2604.04247v12026
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
Roman Novak, Lechao Xiao, Jaehoon Lee +6
stat.MLcs.AIcs.LGarXiv:1810.05148v42018
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
Matteo He, William F. Shen, Xinchi Qiu +1
cs.CLcs.AIcs.LGarXiv:2609.01936v12026
Part-based Graph Convolutional Network for Action Recognition
Kalpit Thakkar, P J Narayanan
cs.CVcs.AIarXiv:1809.04983v12018
A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
Anastasios N. Angelopoulos, Stephen Bates
cs.LGcs.AImath.STarXiv:2107.07511v62021
Probing Factual Knowledge Transfer with Training Data Interventions
Romina Oji, Marc Braun, Marcel Bollmann +2
cs.CLcs.AIarXiv:2609.01341v12026
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
Yuejiang Liu, Fan Feng, Lingjing Kong +6
cs.LGcs.AIcs.ROarXiv:2604.01985v22026
3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation
Qiao Zheng, Hervé Delingette, Nicolas Duchateau +1
cs.CVcs.AIcs.LGarXiv:1804.09400v12018
Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch +3
cs.CLcs.AIcs.NEarXiv:1804.09299v22018
Automatic Image-Level Morphological Trait Annotation for Organismal Images
Vardaan Pahuja, Samuel Stevens, Alyson East +2
cs.CVcs.AIarXiv:2604.01619v32026
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Haechan Kim, Yoonho Lee, Gisang Lee +2
cs.LGcs.AIarXiv:2609.00196v12026
Learning a SAT Solver from Single-Bit Supervision
Daniel Selsam, Matthew Lamm, Benedikt Bünz +3
cs.AIcs.LGcs.LOarXiv:1802.03685v42018
Experiential Reflective Learning for Self-Improving LLM Agents
Marc-Antoine Allard, Arnaud Teinturier, Victor Xing +1
cs.LGcs.AIarXiv:2603.24639v22026
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Qijia He, Xunmei Liu, Hammaad Memon +6
cs.CVcs.AIarXiv:2603.24575v22026
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
Hayeon Kim, Ji Ha Jang, Junghun James Kim +1
cs.CVcs.AIarXiv:2603.22042v32026
Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization
Yutian Jiang, Ruijie Li, Sisuo Lyu +4
cs.AIcs.MMarXiv:2608.29880v12026
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
Liang Ding
cs.AIcs.CLarXiv:2603.21357v42026
Background-Free Objectness Learning for Class-Agnostic Detection
Dania Batool, Liliana Lo Presti, Marco La Cascia +1
cs.CVcs.AIcs.ROarXiv:2608.29232v12026
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
Shengda Fan, Xuyan Ye, Yupeng Huo +9
cs.AIarXiv:2603.14465v22026
Active learning machine learns to create new quantum experiments
Alexey A. Melnikov, Hendrik Poulsen Nautrup, Mario Krenn +4
quant-phcs.AIstat.MLarXiv:1706.00868v32017
MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee +4
cs.SDcs.AIeess.ASarXiv:2506.18729v22025
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
Zuhao Zhang, Chengyue Yu, Yuante Li +3
cs.AIarXiv:2603.09652v32026
Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction
Yu-Lin Tsai, Yu-An Lu, Ci-Yang Tsai +3
cs.CRcs.AIcs.LGarXiv:2608.26733v12026
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
Jiaxuan Lu, Kong Wang, Yemin Wang +9
cs.AIarXiv:2603.08262v22026
Candidate supply and answer selection shape the value of LLM judging in multi-agent systems
Jia-Hao Ji, Sijie Li, Jiabei Cheng +3
cs.AIcs.MAarXiv:2608.25937v12026
AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
Che Wang, Jiaming Zhang, Ziqi Zhang +6
cs.CRcs.AIarXiv:2602.20720v12026
ReIn: Conversational Error Recovery with Reasoning Inception
Takyoung Kim, Jinseok Nam, Chandrayee Basu +5
cs.CLcs.AIarXiv:2602.17022v12026
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
Junchen Ding, Jialiang Dong, Yichen Zhu +5
cs.CRcs.AIarXiv:2608.25667v12026
GENIUS: Generative Fluid Intelligence Evaluation Suite
Ruichuan An, Sihan Yang, Ziyu Guo +8
cs.LGcs.AIcs.CVarXiv:2602.11144v12026
AudioLens: Multi-Perspective Speech Clustering with Reasoning Audio-Language Models
Wenjun Huang, Qiaosong Chu, Tiger Shao +11
cs.SDcs.AIarXiv:2608.25177v12026
FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs
Ze Sheng, Aleksandar Kezic, Zhicheng Chen +1
cs.AIcs.CRcs.LGarXiv:2608.25158v12026
Towards Agentic Intelligence for Materials Science
Huan Zhang, Yizhan Li, Wenhao Huang +18
cond-mat.mtrl-scics.AIarXiv:2602.00169v22026
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
Alexander Hägele, Aryo Pradipta Gema, Henry Sleight +2
cs.AIarXiv:2601.23045v22026
What is Wrong with Topic Modeling? (and How to Fix it Using Search-based Software Engineering)
Amritanshu Agrawal, Wei Fu, Tim Menzies
cs.SEcs.AIcs.CLarXiv:1608.08176v42016
More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight
Yuchen Han, Cheng Yan, Wuyang Zhang
cs.AIarXiv:2608.23941v12026
LUCAID: Agentic Multimodal AI for Lung Cancer Precision Pathology
Marie-Lisa Eich, Kai Standvoss, Timo Milbich +30
cs.CVcs.AIcs.LGarXiv:2608.23803v12026
Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
Yiju Guo, Tianyi Hu, Zexu Sun +1
cs.LGcs.AIcs.CLarXiv:2601.21244v32026
Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
Yiting Shen, Kun Li, Wei Zhou +1
cs.CLcs.AIarXiv:2601.19935v12026
From Generation to Simulation: How Far Are World Models from Being True Simulators?
Tong Wang, Huan Deng, Mucheng Yang +3
cs.AIcs.CVarXiv:2608.23070v12026
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Geo Ahn, Inwoong Lee, Taeoh Kim +3
cs.CVcs.AIarXiv:2601.16211v32026
Summaries:한국어
Deep Knowledge Tracing
Chris Piech, Jonathan Spencer, Jonathan Huang +4
cs.AIcs.CYcs.LGarXiv:1506.05908v12015
Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B
Defu Lin, Wenhui Chen, Ziyao Lin +3
cs.AIarXiv:2608.22975v12026
Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments
Yuki Murakami, Takumi Hattori, Kohsuke Kubota
stat.MEcs.AIcs.LGarXiv:2608.22024v12026
Transition Matching Distillation for Fast Video Generation
Weili Nie, Julius Berner, Nanye Ma +3
cs.CVcs.AIcs.LGarXiv:2601.09881v22026
MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness
Ashutosh Hathidara, Julien Yu, Vaishali Senthil +2
cs.AIcs.LGarXiv:2601.08118v32026
On the Role of Citations in Preference Data
Yu Hou, Hal Daumé, Rachel Rudinger +1
cs.CLcs.AIarXiv:2608.21376v12026
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
Linhao Zhong, Linyu Wu, Bozhen Fang +6
cs.CLcs.AIarXiv:2601.07351v22026
CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models
Bokai Zhao, Yiyang Zhang, Hanqing Chao +6
cs.AIcs.CVarXiv:2608.21060v12026
Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
Chengyuan Yang, Zequn Sun, Wei Wei +1
cs.CLcs.AIarXiv:2601.04463v22026
MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation
Ziwu Liu, Guozhong Li, Chen Qiu +2
cs.CLcs.AIarXiv:2608.20927v12026
CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
Piyush Jha, Jake Rudolph, Victoria Knapp-Pérez +3
cs.AIcs.LGcs.LOarXiv:2608.20686v12026
The Principles of Diffusion Models
Chieh-Hsin Lai, Yang Song, Dongjun Kim +2
cs.LGcs.AIcs.GRarXiv:2510.21890v32025
Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure
Yuchen Wang, Zhongzhi Luan
cs.CLcs.AIarXiv:2608.20361v12026
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
Chang Liu, Chaoyang Ning, Dayi Jiang +32
cs.CLcs.AIarXiv:2608.20350v12026

Artificial Intelligence

NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment

Trustworthy AI: From Principles to Practices

Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models

Log-based Anomaly Detection Without Log Parsing

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens

Part-based Graph Convolutional Network for Action Recognition

A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification

Probing Factual Knowledge Transfer with Training Data Interventions

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation

Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

Automatic Image-Level Morphological Trait Annotation for Organismal Images

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Learning a SAT Solver from Single-Bit Supervision

Experiential Reflective Learning for Self-Improving LLM Agents

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models

Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization

AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Background-Free Objectness Learning for Class-Agnostic Detection

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

Active learning machine learns to create new quantum experiments

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners

MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants

Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use

Candidate supply and answer selection shape the value of LLM judging in multi-agent systems

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

ReIn: Conversational Error Recovery with Reasoning Inception

AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

GENIUS: Generative Fluid Intelligence Evaluation Suite

AudioLens: Multi-Perspective Speech Clustering with Reasoning Audio-Language Models

FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs

Towards Agentic Intelligence for Materials Science

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

What is Wrong with Topic Modeling? (and How to Fix it Using Search-based Software Engineering)

More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight

LUCAID: Agentic Multimodal AI for Lung Cancer Precision Pathology

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents

From Generation to Simulation: How Far Are World Models from Being True Simulators?

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Deep Knowledge Tracing

Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B

Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments

Transition Matching Distillation for Fast Video Generation

MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness

On the Role of Citations in Preference Data

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents

MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation

CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery

The Principles of Diffusion Models

Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel