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)

20,041 to 20,100 of 27,684

From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Wenkang Wei, Yuan Fang, Renhe Jiang +2
cs.AIarXiv:2609.11859v12026
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Cheng Qian, Kunlun Zhu, Beibin Li +2
cs.AIcs.CLcs.LGarXiv:2609.38143v12026
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
Jiaxuan Jiang, Liyuan He, Zhixuan Fang
cs.AIcs.LGarXiv:2609.18779v12026
BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows
Sheng Hong, Yixuan Huang, Weiwei Jiang +3
cs.CRcs.AIarXiv:2608.14126v12026
Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics
Open-H-Embodiment Consortium, :, Nigel Nelson +213
cs.ROcs.AIarXiv:2604.21017v32026
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Taebong Kim, Youngsik Hong, Minsik Kim +4
cs.NEcs.AIarXiv:2605.14386v12026
Lipschitz-constrained Unsupervised Skill Discovery
Seohong Park, Jongwook Choi, Jaekyeom Kim +2
cs.LGcs.AIcs.ROarXiv:2202.00914v22022
Cross-Domain Industrial Fault Detection by Causal Mechanism Monitoring
Dhiraj Neupane, Mohamed Reda Bouadjenek, Richard Dazeley +1
cs.AIarXiv:2608.14666v12026
Measuring AI Ability to Complete Long Software Tasks
Thomas Kwa, Ben West, Joel Becker +23
cs.AIcs.LGarXiv:2503.14499v42025
SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment
Sihang Jiang, Lipeng Ma, Zhonghua Hong +9
cs.AIarXiv:2604.08988v32026
KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation
Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia +2
cs.CLcs.AIarXiv:2109.06243v12021
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments
Ming Dai, Enhui Zheng, Zhenhua Feng +2
cs.CVcs.AIarXiv:2201.09201v22022
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1
cs.CRcs.AIcs.CLarXiv:2604.07223v22026
EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning
Yue Jiang, Zixin Guo, Hamed Rezazadegan Tavakoli +2
cs.CVcs.AIcs.HCarXiv:2404.10163v22024
Summaries:한국어
KV-Kaizen: Learning Context-Adaptive Cache Compression Choices
Joao Monteiro, Louis Béthune, Anastasiia Filippova +3
cs.AIarXiv:2609.37988v12026
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Seojeong Park, Jiho Choi, Junyong Kang +3
cs.CVcs.AIarXiv:2606.02578v12026
Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs
Zhouliang Xie, Changliang Zhou, Genghui Li +1
cs.AIarXiv:2610.03316v12026
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić +1
cs.LGcs.AIarXiv:2604.02270v22026
Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection
Shumin Deng, Ningyu Zhang, Jiaojian Kang +3
cs.CLcs.AIcs.IRarXiv:1910.11621v22019
The Natural Language Decathlon: Multitask Learning as Question Answering
Bryan McCann, Nitish Shirish Keskar, Caiming Xiong +1
cs.CLcs.AIcs.LGarXiv:1806.08730v12018
2D Gaussian Splatting with Semantic Alignment for Image Inpainting
Hongyu Li, Chaofeng Chen, Xiaoming Li +1
cs.CVcs.AIarXiv:2509.01964v12025
Unsupervised Question Decomposition for Question Answering
Ethan Perez, Patrick Lewis, Wen-tau Yih +2
cs.CLcs.AIcs.LGarXiv:2002.09758v32020
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
Marcantonio Bracale Syrnikov, Federico Pierucci, Marcello Galisai +6
cs.GTcs.AIarXiv:2601.11369v22026
Discovering and Achieving Goals via World Models
Russell Mendonca, Oleh Rybkin, Kostas Daniilidis +2
cs.LGcs.AIcs.CVarXiv:2110.09514v12021
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
Xianghe Pang, Shuo Tang, Rui Ye +4
cs.CLcs.AIcs.CYarXiv:2402.05699v32024
Learning Operators with Coupled Attention
Georgios Kissas, Jacob Seidman, Leonardo Ferreira Guilhoto +3
cs.LGcs.AIphysics.comp-pharXiv:2201.01032v12022
Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors
Ruihan Zhang, Prashan Madumal, Tim Miller +2
cs.CVcs.AIcs.LGarXiv:2006.15417v42020
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
Xiaochong Jiang, Shiqi Yang, Ziwei Li +3
cs.CRcs.AIarXiv:2605.26542v42026
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Bo Peng, Ruichong Zhang, Daniel Goldstein +15
cs.CLcs.AIcs.LGarXiv:2503.14456v22025
Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices
Ali Aliev, Maxim Rakhuba
cs.LGcs.AIcs.NAarXiv:2609.27982v12026
Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
YuXuan Liu, Abhishek Gupta, Pieter Abbeel +1
cs.LGcs.AIcs.CVarXiv:1707.03374v22017
Confidence-Aware Multi-Teacher Knowledge Distillation
Hailin Zhang, Defang Chen, Can Wang
cs.LGcs.AIarXiv:2201.00007v32021
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Jiahao Wu, Ning Lu, Shengcai Liu +6
cs.LGcs.AIarXiv:2603.25184v32026
UIBert: Learning Generic Multimodal Representations for UI Understanding
Chongyang Bai, Xiaoxue Zang, Ying Xu +4
cs.CVcs.AIarXiv:2107.13731v22021
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
Chan Hee Song, Jiaman Wu, Clayton Washington +3
cs.AIcs.CLcs.CVarXiv:2212.04088v32022
Volumetric and Multi-View CNNs for Object Classification on 3D Data
Charles R. Qi, Hao Su, Matthias Niessner +3
cs.CVcs.AIarXiv:1604.03265v22016
TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble
Pengfei He, Jiayuan Zhou, Shaowei Wang +1
cs.SEcs.AIarXiv:2610.10242v12026
Keep Me Updated! Memory Management in Long-term Conversations
Sanghwan Bae, Donghyun Kwak, Soyoung Kang +7
cs.CLcs.AIarXiv:2210.08750v12022
Rethinking the Diffusion Model from a Langevin Perspective
Candi Zheng, Yuan Lan
cs.LGcs.AIcs.CVarXiv:2604.10465v12026
Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
Antonius Bima Murti Wijaya, Paul Henderson, Marwa Mahmoud
cs.AIcs.CVarXiv:2603.18166v12026
Physically Consistent Neural Networks for building thermal modeling: theory and analysis
Loris Di Natale, Bratislav Svetozarevic, Philipp Heer +1
cs.LGcs.AIcs.SYarXiv:2112.03212v32021
IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil
Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi +4
cs.CLcs.AIarXiv:2608.29919v12026
AI Agent Systems: Architectures, Applications, and Evaluation
Bin Xu
cs.AIarXiv:2601.01743v12026
The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
Gonçalo Paulo, Louis Jaburi, Nora Belrose +2
cs.CLcs.AIarXiv:2609.37914v12026
Neural networks are more modular than single neurons suggest
Shreya Saha, Benjamin Bergen, Meenakshi Khosla
cs.AIarXiv:2610.12842v12026
Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
Runqian Wang, Yilun Du
cs.LGcs.AIcs.CVarXiv:2510.02300v32025
Pixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics
Abhishek Pillai, Ekta Prashnani, Joohwan Kim +1
cs.AIcs.CVarXiv:2609.37907v22026
Post-Edit Re-Verification in Simulator-Backed Engineering Agents: A Controlled Comparison of Verification-Cadence Guidance
Qingchuan Zhu, Shuyue Tong, Pengju Ren
cs.SEcs.AIarXiv:2608.28147v12026
Learning to Detect Language Model Training Data via Active Reconstruction
Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov +2
cs.LGcs.AIcs.CLarXiv:2602.19020v12026
Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors
Paul S. Scotti, Atmadeep Banerjee, Jimmie Goode +9
cs.CVcs.AIq-bio.NCarXiv:2305.18274v22023
MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
Jiaxi Li, Yucheng Shi, Xiao Huang +2
cs.AIarXiv:2510.03632v22025
Beyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction
Shivang Chopra, Fotis Iliopoulos, Zsolt Kira +1
cs.LGcs.AIarXiv:2609.37905v12026
Controllable Affective Generation via Latent Vector Steering
Xixian Yong, Siyuan Chang, Yingying Zhang +2
cs.CLcs.AIarXiv:2608.25569v12026
Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
Zhongming Yu, Naicheng Yu, Hejia Zhang +5
cs.ARcs.AIcs.MAarXiv:2603.10062v22026
Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution
Judea Pearl
cs.LGcs.AIstat.MLarXiv:1801.04016v12018
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi +3
cs.LGcs.AIarXiv:2511.04217v12025
Evolving Inspectable O-RAN Slicing xApps with LLMs
Faezeh Dehghan Tarzjani, Bhaskar Krishnamachari
eess.SYcs.AIcs.LGarXiv:2609.27337v12026
Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects
Samir Passi, Steven J. Jackson
cs.CYcs.AIcs.LGarXiv:2002.03389v12020
FlowReasoner: Reinforcing Query-Level Meta-Agents
Hongcheng Gao, Yue Liu, Yufei He +6
cs.AIarXiv:2504.15257v12025
The Complexity of Circumscription in DLs
Piero A. Bonatti, Carsten Lutz, Frank Wolter
cs.LOcs.AIarXiv:1401.3476v12014

Artificial Intelligence

From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows

Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Lipschitz-constrained Unsupervised Skill Discovery

Cross-Domain Industrial Fault Detection by Causal Mechanism Monitoring

Measuring AI Ability to Complete Long Software Tasks

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation

Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning

KV-Kaizen: Learning Context-Adaptive Cache Compression Choices

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

The Natural Language Decathlon: Multitask Learning as Question Answering

2D Gaussian Splatting with Semantic Alignment for Image Inpainting

Unsupervised Question Decomposition for Question Answering

Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs

Discovering and Achieving Goals via World Models

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation

Learning Operators with Coupled Attention

Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors

ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Confidence-Aware Multi-Teacher Knowledge Distillation

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

UIBert: Learning Generic Multimodal Representations for UI Understanding

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Volumetric and Multi-View CNNs for Object Classification on 3D Data

TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble

Keep Me Updated! Memory Management in Long-term Conversations

Rethinking the Diffusion Model from a Langevin Perspective

Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering

Physically Consistent Neural Networks for building thermal modeling: theory and analysis

IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil

AI Agent Systems: Architectures, Applications, and Evaluation

The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment

Neural networks are more modular than single neurons suggest

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

Pixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics

Post-Edit Re-Verification in Simulator-Backed Engineering Agents: A Controlled Comparison of Verification-Cadence Guidance

Learning to Detect Language Model Training Data via Active Reconstruction

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information

Beyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction

Controllable Affective Generation via Latent Vector Steering

Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution

The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms

Evolving Inspectable O-RAN Slicing xApps with LLMs

Trust in Data Science: Collaboration, Translation, and Accountability in Corporate Data Science Projects

FlowReasoner: Reinforcing Query-Level Meta-Agents

The Complexity of Circumscription in DLs