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)

18,661 to 18,720 of 27,520

DreamGen: Unlocking Generalization in Robot Learning through Video World Models
Joel Jang, Seonghyeon Ye, Zongyu Lin +25
cs.ROcs.AIcs.LGarXiv:2505.12705v22025
Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning
Lirui Luo, Kelong Mao, Heming Xia +10
cs.LGcs.AIcs.CLarXiv:2609.34422v12026
MojiTalk: Generating Emotional Responses at Scale
Xianda Zhou, William Yang Wang
cs.CLcs.AIarXiv:1711.04090v22017
JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents
Gangyi Li, LuYao Wang, Jingfu Sun +7
cs.ROcs.AIcs.LGarXiv:2610.12957v12026
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Kai Yang, Xin Xu, Yangkun Chen +5
cs.LGcs.AIarXiv:2511.15248v22025
Corrective Machine Unlearning
Shashwat Goel, Ameya Prabhu, Philip Torr +2
cs.LGcs.AIcs.CRarXiv:2402.14015v22024
CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support
Muhammad Muhtasim Shahriar, Md. Naimur Asif Borno, Saad Aloteibi +1
cs.CVcs.AIarXiv:2609.31326v12026
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Guoheng Sun, Kaixi Feng, Shwai He +8
cs.ROcs.AIarXiv:2606.27755v12026
LLM-3D Print: Large Language Models To Monitor and Control 3D Printing
Yayati Jadhav, Peter Pak, Amir Barati Farimani
cs.CLcs.AIcs.LGarXiv:2408.14307v32024
Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
Sarah Tan, Rich Caruana, Giles Hooker +1
stat.MLcs.AIcs.LGarXiv:1710.06169v42017
CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
Bo Qu, Mingguang Chen
cs.AIcs.LGq-fin.CParXiv:2606.29771v32026
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Gaston Besanson
cs.SEcs.AIcs.CYarXiv:2608.18360v12026
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Renjie Mao, Xiangxin Zhou, Lvfang Tao +7
cs.LGcs.AIarXiv:2606.10968v22026
A Mathematical Theory of Pragmatic Information
Kai Niu, Ping Zhang
cs.ITcs.AIcs.ROarXiv:2609.10986v12026
Overcoming the Curvature Bottleneck in MeanFlow
Xinxi Zhang, Shiwei Tan, Quang Nguyen +7
cs.CVcs.AIarXiv:2511.23342v32025
Neural Combinatorial Optimization with Reinforcement Learning
Irwan Bello, Hieu Pham, Quoc V. Le +2
cs.AIcs.LGstat.MLarXiv:1611.09940v32016
Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
Haibo Jin, Peng Kuang, Ye Yu +2
cs.MAcs.AIcs.CLarXiv:2602.03695v22026
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
Fangyuan Xu, Rujun Han, Yanfei Chen +7
cs.AIarXiv:2601.18202v12026
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
Fangzhou Wu, Sandeep Silwal, Qiuyi Zhang
cs.AIcs.LGarXiv:2605.17110v22026
Spurious Rewards: Rethinking Training Signals in RLVR
Rulin Shao, Shuyue Stella Li, Rui Xin +11
cs.AIcs.LGarXiv:2506.10947v22025
Sever: A Robust Meta-Algorithm for Stochastic Optimization
Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane +3
cs.LGcs.AIcs.DSarXiv:1803.02815v22018
Bit-pragmatic Deep Neural Network Computing
J. Albericio, P. Judd, A. Delmás +2
cs.LGcs.AIcs.ARarXiv:1610.06920v12016
Stealing Reasoning Traces from Proprietary LLM APIs
Alexander Panfilov, David Schmotz, Ilia Shumailov +5
cs.CRcs.AIcs.LGarXiv:2608.09867v12026
Summaries:한국어
Towards Defining, Measuring, and Leveraging Creativity in AI Applications
Jingyi Yang, Alexander Tuzhilin
cs.AIarXiv:2610.12845v12026
A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning
Chongwen Dong, Mithun Paul Saint-Germain, Pinjari Asif +1
cs.ROcs.AIarXiv:2609.05133v12026
Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator
Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban
cs.CLcs.AIarXiv:2608.22432v12026
COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
Kavinda Kehelella, Sanghamitra Dutta
cs.CLcs.AIcs.LGarXiv:2610.12837v12026
UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
Yonglin Tian, Fei Lin, Yiduo Li +11
cs.ROcs.AIarXiv:2501.02341v22025
SWE-Game: Can Coding Agents Build the Games We Want?
Xiaoyu Chen, Lai Wei, Jin Wang +8
cs.AIarXiv:2609.33678v32026
Representation Learning on Graphs with Jumping Knowledge Networks
Keyulu Xu, Chengtao Li, Yonglong Tian +3
cs.LGcs.AIcs.CVarXiv:1806.03536v22018
Adapting a Kidney Exchange Algorithm to Align with Human Values
Rachel Freedman, Jana Schaich Borg, Walter Sinnott-Armstrong +2
cs.AIarXiv:2005.09755v12020
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
cs.LGcs.AIcs.CLarXiv:2608.12307v12026
PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
Ram Ramrakhya, Dhruv Batra, Erik Wijmans +1
cs.LGcs.AIcs.ROarXiv:2301.07302v22023
Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search
Khubaib Ahmed, Ahsan Adeel, Nasir Saleem +3
cs.SDcs.AIeess.ASarXiv:2610.12796v12026
Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
Ruikang Liu, Yuxuan Sun, Manyi Zhang +5
cs.CLcs.AIarXiv:2504.04823v22025
GRACE:Gradient-guided Coreset Selection for LLM Unlearning
Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro +1
cs.AIcs.LGarXiv:2608.28361v12026
Structure-Mapping-Guided Self-Explanation for Learning Mathematical Procedures
Shinhaeng Lee, Christopher J. MacLellan, Daniel Weitekamp
cs.AIarXiv:2609.33079v12026
Long-form factuality in large language models
Jerry Wei, Chengrun Yang, Xinying Song +9
cs.CLcs.AIcs.LGarXiv:2403.18802v42024
Toward Scalable Terminal Task Synthesis via Skill Graphs
Zhiyuan Fan, Tinghao Yu, Yuanjun Cai +8
cs.AIarXiv:2604.25727v12026
On the estimation and validity of AI time horizons---a statistical look at the METR plot
Drew T. Nguyen, William Fithian
cs.AIarXiv:2610.12466v12026
The Polytopal Neural Network
A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2
cs.LGcs.AIarXiv:2610.12004v12026
GPT-4V(ision) is a Generalist Web Agent, if Grounded
Boyuan Zheng, Boyu Gou, Jihyung Kil +2
cs.IRcs.AIcs.CLarXiv:2401.01614v22024
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Shicheng Xu, Liang Pang, Mo Yu +4
cs.CLcs.AIcs.IRarXiv:2402.18150v22024
PACT: From Credit Assignment to Critic Alignment
Jiayan Fu, Hang Xu, Yong Zhang +4
cs.LGcs.AIarXiv:2609.26355v12026
One-Class Adversarial Nets for Fraud Detection
Panpan Zheng, Shuhan Yuan, Xintao Wu +2
cs.LGcs.AIcs.CRarXiv:1803.01798v22018
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi
cs.AIcs.CLcs.LGarXiv:2606.10740v22026
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba +2
cs.LGcs.AIarXiv:2610.12445v12026
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
Jianlan Luo, Zheyuan Hu, Charles Xu +7
cs.ROcs.AIarXiv:2401.16013v42024
Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs
Zhuo Yang, Daolang Wang, Lingli Ge +3
cs.AIarXiv:2505.12833v22025
IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao +4
cs.LGcs.AIcs.CVarXiv:2103.12308v12021
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents
Jize Wang, Han Wu, Zhiyuan You +9
cs.AIarXiv:2601.18130v12026
ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
Xuanzhi Liu, Xinyi Wu, Hang Pan +4
cs.CVcs.AIarXiv:2609.31509v12026
Machine Unlearning of Pre-trained Large Language Models
Jin Yao, Eli Chien, Minxin Du +4
cs.CLcs.AIcs.CRarXiv:2402.15159v32024
Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
William Lugoloobi, Samuelle Marro, Jabez Magomere +2
cs.CRcs.AIcs.HCarXiv:2605.14786v12026
Exploratory Combinatorial Optimization with Reinforcement Learning
Thomas D. Barrett, William R. Clements, Jakob N. Foerster +1
cs.LGcs.AIstat.MLarXiv:1909.04063v22019
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training
Joe Stacey, Pasquale Minervini, Haim Dubossarsky +2
cs.LGcs.AIcs.CLarXiv:2004.07790v52020
Irreducible Curriculum for Language Model Pretraining
Simin Fan, Martin Jaggi
cs.CLcs.AIcs.LGarXiv:2310.15389v12023
Learning Convolutional Neural Networks for Graphs
Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov
cs.LGcs.AIstat.MLarXiv:1605.05273v42016
Closed-form Continuous-time Neural Models
Ramin Hasani, Mathias Lechner, Alexander Amini +5
cs.LGcs.AIcs.NEarXiv:2106.13898v22021
ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
Xin Wang, Hector Delgado, Hemlata Tak +10
eess.AScs.AIcs.SDarXiv:2408.08739v12024

Artificial Intelligence

DreamGen: Unlocking Generalization in Robot Learning through Video World Models

Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning

MojiTalk: Generating Emotional Responses at Scale

JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

Corrective Machine Unlearning

CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support

Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

LLM-3D Print: Large Language Models To Monitor and Control 3D Printing

Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation

CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

A Mathematical Theory of Pragmatic Information

Overcoming the Curvature Bottleneck in MeanFlow

Neural Combinatorial Optimization with Reinforcement Learning

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems

SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback

Capturing LLM Capabilities via Evidence-Calibrated Query Clustering

Spurious Rewards: Rethinking Training Signals in RLVR

Sever: A Robust Meta-Algorithm for Stochastic Optimization

Bit-pragmatic Deep Neural Network Computing

Stealing Reasoning Traces from Proprietary LLM APIs

Towards Defining, Measuring, and Leveraging Creativity in AI Applications

A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning

Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator

COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering

UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility

SWE-Game: Can Coding Agents Build the Games We Want?

Representation Learning on Graphs with Jumping Knowledge Networks

Adapting a Kidney Exchange Algorithm to Align with Human Values

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav

Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

GRACE:Gradient-guided Coreset Selection for LLM Unlearning

Structure-Mapping-Guided Self-Explanation for Learning Mathematical Procedures

Long-form factuality in large language models

Toward Scalable Terminal Task Synthesis via Skill Graphs

On the estimation and validity of AI time horizons---a statistical look at the METR plot

The Polytopal Neural Network

GPT-4V(ision) is a Generalist Web Agent, if Grounded

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation

PACT: From Credit Assignment to Critic Alignment

One-Class Adversarial Nets for Fraud Detection

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs

IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents

ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos

Machine Unlearning of Pre-trained Large Language Models

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

Exploratory Combinatorial Optimization with Reinforcement Learning

Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training

Irreducible Curriculum for Language Model Pretraining

Learning Convolutional Neural Networks for Graphs

Closed-form Continuous-time Neural Models

ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale