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)

14,941 to 15,000 of 15,225

Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +23
cs.CVcs.AIcs.GRarXiv:2607.04443v32026
Building to the Test: Coding Agents Deliver What You Check, Not What You Requested
Yanuo Ma, Ben Kereopa-Yorke, Ben Schultz
cs.SEcs.AIarXiv:2606.28430v12026
Measuring the Gap Between Human and LLM Research Ideas
Ziyu Chen, Yilun Zhao, Arman Cohan
cs.CLcs.AIarXiv:2607.01233v12026
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling
Yong Yi Bay, Kathleen A. Yearick
cs.LGcs.AIcs.CLarXiv:2606.28661v12026
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting
Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin +3
quant-phcs.AIcs.LGarXiv:2606.27821v12026
ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models
Karan Goyal, Afreen Hossain, Debojyoti Das +1
cs.CVcs.AIcs.CLarXiv:2607.20092v12026
Measuring Cross-Task Behavioral Consistency in Language Model Agents
Amritesh Banerjee, Pranil Raichura
cs.AIarXiv:2608.13598v12026
No Universal Signal Predicts Sample-Level LLM Regression under Version Updates
Jia Sheng, Yiwei Lu
cs.AIcs.CLcs.LGarXiv:2608.13607v12026
Optimal Power Allocation and AI Receiver Design for Superimposed DMRS and Data Transmission
Sha Hu, Zhongwang Fu
cs.ITcs.AIarXiv:2608.13809v12026
Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline
Joào Pedro Monteiro Pereira, Vinicius Cardoso Garcia
cs.SEcs.AIcs.LGarXiv:2608.13742v12026
SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
Zhongsheng Wang, Zhedong Lin, Qian Liu +2
cs.AIarXiv:2608.13820v12026
Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation
Ajay Pravin Mahale
cs.AIarXiv:2608.13754v12026
Ontology-Grounded Project Memory for Coding Agents
James Adam
cs.AIcs.SEarXiv:2608.13662v12026
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
Dekun Yang
cs.AIcs.CLcs.LGarXiv:2608.13626v12026
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Tuo Liang, Zhe Hu, Disheng Liu +2
cs.CLcs.AIcs.MMarXiv:2607.19011v12026
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
Yimeng Chen, Nathanaël Denis, Roberto Di Pietro +1
cs.CRcs.AIcs.CLarXiv:2607.17986v12026
Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
Shyamal Y. Dharia, Stephen D. Smith, Camilo E. Valderrama
cs.LGcs.AIarXiv:2607.18149v12026
AI Tour Meeting: Group Travel Planning by LLM Agents
Daisuke Kikuta
cs.AIcs.CLcs.MAarXiv:2607.18806v12026
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
Hiskias Dingeto
cs.AIcs.CLarXiv:2607.20379v12026
EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration
Jia-Kai Dong, Yi-Cheng Lin, Hung-yi Lee
cs.HCcs.AIarXiv:2607.18529v22026
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Mei Yuan, Qi Long, Qifeng Wu +5
cs.CVcs.AIcs.CLarXiv:2607.18142v12026
TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward
Debottam Dutta, Jaehoon Hahm, Jianchong Chen +1
cs.AIarXiv:2607.21606v12026
Robostral Navigate
Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra +273
cs.ROcs.AIarXiv:2607.20785v32026
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu +7
cs.AIcs.CLarXiv:2607.21557v32026
A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
Sietse Schelpe
cs.CLcs.AIcs.IRarXiv:2607.23806v12026
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
Nuemaan Malik
cs.LGcs.AIarXiv:2607.19058v22026
OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis
Zihan Li, Feiyang Liu, Dandan Shan +2
cs.CVcs.AIcs.LGarXiv:2607.25108v12026
Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model
Markus J. Buehler
cs.AIcond-mat.mes-hallcond-mat.mtrl-sciarXiv:2607.20058v12026
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
Lehan Wang, Boli Chen, Ruixue Ding +7
cs.CRcs.AIcs.CLarXiv:2607.26791v12026
Distilled Reinforcement Learning for LLM Post-training
Chen Wang, Zhaochun Li, Jionghao Bai +4
cs.LGcs.AIarXiv:2607.17247v12026
Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning
Qiangqiang He, Zhongheng Wu, ZiJian Wang
cs.AIarXiv:2607.27888v12026
CriPO: Enhancing Rubric-based RL via Self-Distillation
Mingxuan Xia, Yuhang Yang, Chao Ye +7
cs.LGcs.AIarXiv:2607.18082v32026
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
Zhaokai Wang, Tianlin Gui, Jiayuan Rao +3
cs.AIcs.CLcs.LGarXiv:2607.18084v12026
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
Jiazhen Jiang, Boxi Cao, Lingyong Yan +6
cs.AIcs.CLcs.LGarXiv:2607.19865v12026
AutoIndex: Learning Representation Programs for Retrieval
Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy +3
cs.IRcs.AIcs.CLarXiv:2607.18603v12026
Codifying the Judge: Scalable Evaluation via Program Distillation
Tzu-Heng Huang, Shengqi Qiu, Frederic Sala
cs.AIcs.LGarXiv:2607.22561v12026
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
Haoyang Huang, Wenjie Huang, Tianqi Xu +14
cs.AIarXiv:2607.25669v12026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray
cs.AIcs.CLcs.LGarXiv:2607.25091v12026
SceneActBench: Can Agents Act on the 3D Scenes They See?
Yifei Zhao, Xiangxin Zhou, Wenhao Yang +11
cs.AIcs.CVarXiv:2607.22393v12026
dRAE: Representation Autoencoder with Hyper-Spherical Codes
Tianren Ma, Lin Long, Chuyan Chen +4
cs.CVcs.AIarXiv:2607.22148v12026
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs
Sai Shruthi Sistla, Ashutosh Hathidara, Christopher Toukmaji +2
cs.AIarXiv:2607.22639v12026
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng +21
cs.CVcs.AIcs.LGarXiv:2607.19064v22026
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Pingyu Wu, Lingyao Zhu, Weiming Zhang +1
cs.CRcs.AIarXiv:2607.27951v12026
Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems
Ali Zahid Raja
cs.AIcs.MAarXiv:2607.24117v12026
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
Ads Dawson, Adrian Wood
cs.CRcs.AIarXiv:2607.26314v12026
GPT-Red: Automated Red Teaming via Self-Play at Scale
Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal +15
cs.CRcs.AIcs.CLarXiv:2607.26115v12026
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
Sizhe Zhou, Sheldon Yu, Hui Wei +8
cs.CLcs.AIarXiv:2607.26637v12026
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
Varun Gumma, Navonil Majumder, Soumitra Sinhahajari +1
cs.AIarXiv:2607.22375v12026
Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking
Haorui He, Xinwen Chen, Dacheng Wen +3
cs.CLcs.AIcs.MMarXiv:2607.23514v12026
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han +9
cs.AIcs.CLarXiv:2607.18754v12026
QQWorld: Quantile-Quantile Matching for World Model Regularization
Zhoushun Yu, Xiaoyu Hu, Xiangyu Xu
cs.LGcs.AIcs.CVarXiv:2607.28415v12026
Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation
Zhe Liu
cs.CLcs.AIcs.SDarXiv:2608.13624v12026
Learning-to-Transition for Large-scale and High-Order MIMO Detection
Yubo Zhang, Yiyao Liu, Xiaodong Wang
cs.ITcs.AIarXiv:2608.14511v12026
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Zhicheng Cai, Xinyuan Guo, Hanlin Wu +4
cs.LGcs.AIarXiv:2607.10169v12026
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
Grace Man Chen, Litao Guo, Yifan Wu +5
cs.SEcs.AIcs.CVarXiv:2607.06306v12026
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction
Boyang Zhang, Adrian Lyjak, Eli Stewart +2
cs.AIarXiv:2607.29677v22026
Visual Contrastive Self-Distillation
Yijun Liang, Yunjie Tian, Yijiang Li +4
cs.CVcs.AIarXiv:2607.21556v12026
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Bo-Wen Zhang, Junwei He, Wen Wang +5
cs.AIarXiv:2607.25659v12026
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jingbo Zhou, Yusai Zhao, Qi Bao +12
cs.AIcs.CLcs.HCarXiv:2607.27155v12026
$π\mathbf{R}^2$: Reactive Real-time Flow Policies
Sungjae Park, Shubham Tulsiani
cs.ROcs.AIcs.LGarXiv:2607.26055v12026

Artificial Intelligence

Wan-Streamer v0.2: Higher Resolution, Same Latency

Building to the Test: Coding Agents Deliver What You Check, Not What You Requested

Measuring the Gap Between Human and LLM Research Ideas

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models

Measuring Cross-Task Behavioral Consistency in Language Model Agents

No Universal Signal Predicts Sample-Level LLM Regression under Version Updates

Optimal Power Allocation and AI Receiver Design for Superimposed DMRS and Data Transmission

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

SDO: Subspace Deconflicting Operator for Multi-Adapter Composition

Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation

Ontology-Grounded Project Memory for Coding Agents

A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure

Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices

AI Tour Meeting: Group Travel Planning by LLM Agents

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward

Robostral Navigate

OpenForgeRL: Train Harness-native Agents in Any Environment

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

Distilled Reinforcement Learning for LLM Post-training

Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning

CriPO: Enhancing Rubric-based RL via Self-Distillation

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

AutoIndex: Learning Representation Programs for Retrieval

Codifying the Judge: Scalable Evaluation via Program Distillation

OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

SceneActBench: Can Agents Act on the 3D Scenes They See?

dRAE: Representation Autoencoder with Hyper-Spherical Codes

TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

GPT-Red: Automated Red Teaming via Self-Play at Scale

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

QQWorld: Quantile-Quantile Matching for World Model Regularization

Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation

Learning-to-Transition for Large-scale and High-Order MIMO Detection

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Visual Contrastive Self-Distillation

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

$π\mathbf{R}^2$: Reactive Real-time Flow Policies