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)

15,121 to 15,180 of 15,227

The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
Zhiheng Wang, Bo Peng, Lai Wei +1
cs.AIarXiv:2608.06270v12026
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
cs.AIarXiv:2608.03972v12026
AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution
Simiao Zuo, Chenhui Xu, Yimeng Jia +3
cs.IRcs.AIarXiv:2608.13833v12026
Building AI-Intensive Software with AI: Early Results and a Cautionary Tale on Measuring Development Cost
Victor Barros de Miranda Neves, Kiev Santos da Gama, Vinicius Cardoso Garcia
cs.SEcs.AIcs.LGarXiv:2608.13730v12026
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Yijun Lu, Rui Ye, Jiajun Wang +4
cs.AIarXiv:2608.05102v12026
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Junbo Li, Boyi Liu, Canwen Xu +5
cs.AIarXiv:2608.06714v12026
Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
Yi Ding, Yanzhao Yu, Xili Dai +5
cs.ROcs.AIcs.CVarXiv:2608.14047v12026
GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection
Yingjie Ma, Zitong Yu, Wei Jia +2
cs.CVcs.AIarXiv:2608.14389v12026
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
cs.CVcs.AIarXiv:2608.05131v22026
MameLoshnLM: Yiddish Language Model and Evaluation Benchmark
Uri Katz, Omer Goldman, Tomasz Limisiewicz +2
cs.CLcs.AIarXiv:2608.05850v12026
Continual Learning in Transition
Zhiyan Hou, Dan Zhang, Tao Feng +11
cs.LGcs.AIarXiv:2608.06216v22026
Mitigating Gender Bias in English to Romanian Machine Translation
Ioana Grigore, Sergiu Nisioi
cs.CLcs.AIarXiv:2608.08606v12026
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Changle Qu, Sunhao Dai, Hengyi Cai +4
cs.CLcs.AIarXiv:2608.04007v12026
Retrieval Grounding Latent Reasoning for Dense Retrieval
Gang Zhou, Xiongxi Yu, Hu Tian +5
cs.AIarXiv:2608.14107v12026
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Varun Ursekar, Apaar Shanker, Yash Maurya +4
cs.AIcs.CLcs.LGarXiv:2608.06301v12026
Mind the Long Tail: Understanding the Difficulty of Delay Detection in Business Processes
Keyvan Amiri Elyasi, Lukas Kirchdorfer, Heiner Stuckenschmidt
cs.LGcs.AIarXiv:2608.14367v12026
Designing Sustainable Federated Learning as a Service using Neural Architecture Search
Keya Patel, Sajib Mistry, Sheik Fattah +4
cs.AIarXiv:2608.14359v12026
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Jingsheng Zheng, Xinyuan Fang, Jintian Zhang +3
cs.CLcs.AIcs.HCarXiv:2608.05013v12026
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
Bingxin Yu, Xueli Wang, Jerry Zhou +6
cs.CVcs.AIarXiv:2608.13939v12026
WorldClaw: Agentic 3D Open-World Generation at Scale
Chunchao Guo, Jinpeng Li, Yang Li +1
cs.AIcs.CVarXiv:2608.05248v12026
BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs
Varsha Ramineni, Hossein A. Rahmani, Jerome Ramos +2
cs.AIarXiv:2608.14161v12026
Buy the Rumor, Sell the News: When Is News Priced In?
Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini +2
cs.AIcs.LGq-fin.STarXiv:2608.14014v12026
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Wenyao Cui, Huaping Zhang, Yongyi Huang +6
cs.AIarXiv:2608.08786v12026
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud +2
cs.CLcs.AIarXiv:2608.13706v12026
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
Zikun Qu, Min Zhang, Mingze Kong +4
cs.LGcs.AIarXiv:2608.04419v12026
ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models
Xinye Li, Lingshuai Lin, Lei Wang +8
cs.CVcs.AIarXiv:2608.14022v12026
A Generalized Parallelogram Rule for Proportional Analogies on Riemannian Manifolds
Pierre-Alexandre Murena, Marcelo Hartmann
cs.AIarXiv:2608.14220v12026
From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL
Wenyue Hua, Zachary Huang, Tyler Payne +3
cs.AIcs.CLcs.LGarXiv:2608.13787v12026
Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation
Michael R. Martin, Joseph Insley, Victor A. Mateevitsi +2
cs.CVcs.AIcs.CEarXiv:2608.14112v12026
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
Lu Yang, Shusheng Xu, Zhuoran Li +2
cs.AIarXiv:2608.13921v12026
Multi-Objective Bayesian Optimization for Model Merging
Utkarsh Agarwal, Vamshi Bonagiri, Raul Astudillo +1
cs.LGcs.AIarXiv:2608.14264v12026
How Much Do Legal RAG Systems Still Hallucinate?
Souvick Das, Sallam Abualhaija, Domenico Bianculli
cs.CLcs.AIarXiv:2608.14210v12026
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
Qingren Yao, Yaxuan Kong, Yuqi Nie +6
cs.AIarXiv:2608.14270v12026
Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
Toby D. Pilditch
cs.AIarXiv:2608.14425v12026
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration
Julian Ostermaier, Swann Ruyter, Reuben Dorent +1
cs.AIarXiv:2608.14355v12026
Twin: Playing an Unknown Game with a Test-Time Digital Twin
Alexy Skoutnev, Kirill Acharya, Gaston Longhitano +3
cs.AIarXiv:2608.14490v12026
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
Zhizhao Guan, Chen Huang, Ziming Liu +5
cs.AIcs.LGarXiv:2608.14339v12026
Designing Compact Neural Architectures via Neuron Gating and Mixed Activation
Abhishek Shukla, Ankur Sinha, Faiz Hamid
cs.LGcs.AIarXiv:2608.14443v12026
A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models
Md Kamrul Islam, Tiphaine Henry, Mattia Salnitri +2
cs.CRcs.AIcs.SEarXiv:2608.14370v12026
The Dynamics of Intelligence Explosions
Toby Ord
cs.AIecon.THarXiv:2608.14426v12026
Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Support
Alexandre Cristovão Maiorano
cs.HCcs.AIcs.SEarXiv:2608.13563v12026
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
Shahab Band, Hamed Mohammadi
cs.AIarXiv:2608.14456v12026
The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel
Mohammad Imrul Jubair, Tom Yeh
cs.HCcs.AIarXiv:2608.13572v12026
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
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
William Nixon, Jon Durbin, Florian Standhartinger +2
cs.AIarXiv:2608.13573v12026
Benchmarking data-driven material models on the classic Treloar dataset
Hagen Holthusen, Moritz Flaschel, Denisa Martonová +1
cs.AIcs.CEarXiv:2608.14063v12026
Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi
cs.AIeess.SYarXiv:2608.14306v12026
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
JungMin Yun, YoungBin Kim
cs.CLcs.AIarXiv:2608.13588v12026
Weak-to-Strong Generalization via Direct On-Policy Distillation
Shiyuan Feng, Huan-ang Gao, Haohan Chi +7
cs.LGcs.AIcs.CLarXiv:2607.05394v22026
Summaries:한국어
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3
cs.AIarXiv:2605.28742v22026
Summaries:한국어
Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Procedural Guidance
Rodrigo Gallardo, Qilmeg Doudatcz, Ganit Goldstein +7
cs.HCcs.AIarXiv:2608.13589v12026
Summaries:한국어
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
Bo Jin, Qiang Jiao, Xin Tong
cs.AIcs.MAarXiv:2608.13574v12026
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Thiago Sandoval, Ufuk Topcu
cs.AIcs.CLcs.CRarXiv:2608.14089v12026
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
Pradeep Kumar Sharma, Shantanu Godbole, Hritvik Shrivastava
cs.AIarXiv:2608.13565v12026
CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
Yuji Ren, Chenkai Xu, Zhuocheng Gong +2
cs.LGcs.AIcs.CLarXiv:2608.13925v12026
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
Darragh Quinn, David Dylan, Roisin Healy +3
cs.AIarXiv:2608.13564v12026
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov +9
cs.LGcs.AIcs.SEarXiv:2608.13566v12026
Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through Virtual Sensing
Davide Andrea Guastella, Eladio Montero Porras, Evangelos Pournaras +1
cs.AIarXiv:2608.13993v12026
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
Dayuan Zhao, Shengcao Cao, Yu-Xiong Wang +1
cs.CLcs.AIcs.LGarXiv:2608.13570v12026
ASSERT: A Measurement Pipeline for GenAI Audits
Riccardo Fogliato, Abhinav Palia, Xiawei Wang +11
cs.CLcs.AIcs.CYarXiv:2608.13840v12026

Artificial Intelligence

The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution

Building AI-Intensive Software with AI: Early Results and a Cautionary Tale on Measuring Development Cost

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows

Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use

GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

MameLoshnLM: Yiddish Language Model and Evaluation Benchmark

Continual Learning in Transition

Mitigating Gender Bias in English to Romanian Machine Translation

TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

Retrieval Grounding Latent Reasoning for Dense Retrieval

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Mind the Long Tail: Understanding the Difficulty of Delay Detection in Business Processes

Designing Sustainable Federated Learning as a Service using Neural Architecture Search

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

WorldClaw: Agentic 3D Open-World Generation at Scale

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

Buy the Rumor, Sell the News: When Is News Priced In?

SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

A Generalized Parallelogram Rule for Proportional Analogies on Riemannian Manifolds

From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL

Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation

When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

Multi-Objective Bayesian Optimization for Model Merging

How Much Do Legal RAG Systems Still Hallucinate?

TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments

Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations

Disentangled Shared Representations Improve Morpho-Transcriptomic Integration

Twin: Playing an Unknown Game with a Test-Time Digital Twin

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models

The Dynamics of Intelligence Explosions

Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Decision Support

Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments

The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel

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

A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing

Benchmarking data-driven material models on the classic Treloar dataset

Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety

IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering

Weak-to-Strong Generalization via Direct On-Policy Distillation

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Procedural Guidance

Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents

Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers

Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking

CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required

Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through Virtual Sensing

Think in Latent, Explain in Language: Self-Explainable Latent Reasoning

ASSERT: A Measurement Pipeline for GenAI Audits