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)

5,761 to 5,820 of 15,472

From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
Kelvin Guu, Panupong Pasupat, Evan Zheran Liu +1
cs.AIcs.LGstat.MLarXiv:1704.07926v12017
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Fengli Xu, Qianyue Hao, Zefang Zong +17
cs.AIcs.CLarXiv:2501.09686v32025
Autonomous Drone Racing with Deep Reinforcement Learning
Yunlong Song, Mats Steinweg, Elia Kaufmann +1
cs.ROcs.AIarXiv:2103.08624v22021
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
Zhiyuan Liu, Yicun Yang, Yaojie Zhang +6
cs.LGcs.AIcs.CLarXiv:2506.06295v32025
Multiple decision trees
Suk Wah Kwok, Chris Carter
cs.LGcs.AIstat.MLarXiv:1304.2363v12013
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
Renjun Xu, Yang Yan
cs.MAcs.AIarXiv:2602.12430v42026
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Tilman Räuker, Anson Ho, Stephen Casper +1
cs.LGcs.AIcs.CLarXiv:2207.13243v62022
Composite Monte Carlo Decision Making under High Uncertainty of Novel Coronavirus Epidemic Using Hybridized Deep Learning and Fuzzy Rule Induction
Simon James Fong, Gloria Li, Nilanjan Dey +2
cs.AIq-bio.PEarXiv:2003.09868v12020
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
Ivan Evtimov, Arman Zharmagambetov, Aaron Grattafiori +2
cs.CRcs.AIarXiv:2504.18575v32025
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
NVIDIA, :, Alisson Azzolini +51
cs.AIcs.CVcs.LGarXiv:2503.15558v32025
On the Effects of Data Scale on UI Control Agents
Wei Li, William Bishop, Alice Li +4
cs.AIcs.LGarXiv:2406.03679v62024
Nested Learning: The Illusion of Deep Learning Architectures
Ali Behrouz, Meisam Razaviyayn, Peilin Zhong +1
cs.LGcs.AIarXiv:2512.24695v12025
Evaluation and Benchmarking of LLM Agents: A Survey
Mahmoud Mohammadi, Yipeng Li, Jane Lo +1
cs.LGcs.AIarXiv:2507.21504v12025
mHC: Manifold-Constrained Hyper-Connections
Zhenda Xie, Yixuan Wei, Huanqi Cao +17
cs.CLcs.AIcs.LGarXiv:2512.24880v22025
The Diffusion Duality
Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan +3
cs.LGcs.AIcs.CLarXiv:2506.10892v32025
A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)
Abul Ehtesham, Aditi Singh, Gaurav Kumar Gupta +1
cs.AIarXiv:2505.02279v22025
When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?
Yansen Han, Hongxin Sun, Tao Lin
cs.LGcs.AIarXiv:2608.28010v12026
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Fengqing Jiang, Zhangchen Xu, Yuetai Li +5
cs.AIcs.CLarXiv:2502.12025v12025
Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions
Jing Gu, Eliana Stefani, Qi Wu +2
cs.CVcs.AIcs.CLarXiv:2203.12667v32022
Soft Adaptive Policy Optimization
Chang Gao, Chujie Zheng, Xiong-Hui Chen +7
cs.LGcs.AIcs.CLarXiv:2511.20347v22025
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Polina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri +1
cs.AIarXiv:2506.09038v12025
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
Anjun Gao, Yueyang Quan, Yufei Xia +2
cs.CRcs.AIcs.IRarXiv:2608.23959v12026
Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention
Sergii Kozyrev, Davyd Maiboroda
cs.AIarXiv:2608.23834v12026
Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation
Seunghan Lee, Hyunsik Yoo, Jian Kang +2
cs.AIcs.LGarXiv:2608.22920v12026
Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku
Xiansheng Luo, Chaowei Zhang, Zewei Zhang +2
cs.AIarXiv:2608.22832v12026
Model Hypnosis: Strong control of AI via additive subliminal effects
Enric Boix-Adsera, Benedict Tessler
cs.CLcs.AIarXiv:2608.16834v12026
Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
Yanze Jiang, Mingxuan Li, Yuhao Wang +2
cs.AIarXiv:2608.21027v12026
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Bo Liu, Simon Yu, Yiding Jiang +15
cs.CLcs.AIarXiv:2608.19197v12026
Summaries:한국어
SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL
Xiangqi Wang, Nhan H. Pham, Oktie Hassanzadeh +2
cs.AIarXiv:2608.20630v12026
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
Wei Yu, Suxing Liu, Minjie Yu +4
cs.AIarXiv:2608.18884v12026
CAPO: Constraint-Aware Prompt Optimization for LLM Agents
Victor Ye Dong, Reid Pryzant, Yi Liu +1
cs.CLcs.AIarXiv:2608.16068v12026
Optimal Lower Bounds for Networked Information Aggregation
Ambar Pal
cs.LGcs.AIstat.MLarXiv:2608.15472v12026
Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads
Anubhab Banerjee
cs.AIcs.DCcs.LGarXiv:2608.15117v12026
Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics
Ruochen Liu, Wei Lou
cs.CVcs.AIcs.CLarXiv:2608.14710v12026
AI-Assisted Discovery and Construction of a Counterexample to the Convergence of Three-Block ADMM with the Identity Matrix as its Third Constraint Block
Kenan Xu, Xiangfeng Wang
math.OCcs.AIarXiv:2608.14396v12026
Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions
Xiaokai Yan, Jingtao Ding, Yong Li +1
cs.HCcs.AIarXiv:2608.14132v12026
Musical Mirrors: The LLM as Sounding Board in Songwriting
Xiao Xiao
cs.HCcs.AIarXiv:2608.13944v12026
Jais 2: A Family of Arabic-Centric Open Large Language Models
Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim +57
cs.CLcs.AIarXiv:2608.13580v12026
Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions
Qinglin Yang, Chen Qiu, Hongyuan Zhang +3
cs.LGcs.AIcs.DCarXiv:2608.13844v12026
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
Yongchao Huang
cs.AIarXiv:2608.13621v12026
PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization
Ruogu Chen, Jie Han
cs.LGcs.AIcs.ARarXiv:2608.13790v12026
G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
Yechan Kim, JongHyun Park, Dongho Yoon +2
cs.CVcs.AIarXiv:2607.19942v22026
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Rahul Sajnani, Yulia Gryaditskaya, Radomír Měch +2
cs.CVcs.AIcs.GRarXiv:2607.19344v12026
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Guoxuan Chen, Chufeng Xiao, Haoran Yang +30
cs.CVcs.AIarXiv:2607.13125v22026
Length Penalties Make Chain-of-Thought Less Monitorable
Bryce Little
cs.AIcs.CLcs.LGarXiv:2607.09786v32026
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
Bao Long Nguyen Huu, Atsushi Hashimoto
cs.IRcs.AIarXiv:2607.00052v12026
Confidence-Aware Tool Orchestration for Robust Video Understanding
Yangfan He, Yujin Choi, Jaehong Yoon
cs.CVcs.AIarXiv:2606.26904v12026
Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
Zixin Ding, Shaghayegh Emami, Giovanna Salvi +7
cs.LGcs.AIhep-exarXiv:2606.23993v32026
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos Team, Fei Wang, Shan You +21
cs.AIcs.CVarXiv:2606.16533v32026
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
cs.AIarXiv:2606.24855v12026
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Haipeng Luo, Qingfeng Sun, Songli Wu +4
cs.LGcs.AIcs.CLarXiv:2606.19236v12026
Can Generalist Agents Automate Data Curation?
Feiyang Kang, Hanze Li, Adam Nguyen +5
cs.AIcs.CLcs.CVarXiv:2606.04261v12026
AURA: Action-Gated Memory for Robot Policies at Constant VRAM
Josef Chen
cs.AIcs.ARcs.DCarXiv:2606.02775v12026
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Mingze Wang, Shuchen Zhu, Yuxin Fang +3
cs.LGcs.AIstat.MLarXiv:2605.26895v12026
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
Shuhong Zheng, Michael Oechsle, Erik Sandström +3
cs.CVcs.AIcs.GRarXiv:2605.23892v12026
EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
Rong Wu, Xiaoman Wang, Jianbiao Mei +8
cs.CLcs.AIarXiv:2510.16079v32025
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
Boxuan Zhang, Jianing Zhu, Qifan Wang +2
cs.CVcs.AIcs.LGarXiv:2605.09296v12026
A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
Qingchuan Ma, Yuexiao Ma, Yongkang Xie +3
cs.AIcs.LGarXiv:2605.17278v12026
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Bart Bussmann, Noa Nabeshima, Adam Karvonen +1
cs.LGcs.AIarXiv:2503.17547v12025
Latent Preference Modeling for Cross-Session Personalized Tool Calling
Yejin Yoon, Minseo Kim, Taeuk Kim
cs.CLcs.AIarXiv:2604.17886v12026

Artificial Intelligence

From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Autonomous Drone Racing with Deep Reinforcement Learning

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

Multiple decision trees

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

Composite Monte Carlo Decision Making under High Uncertainty of Novel Coronavirus Epidemic Using Hybridized Deep Learning and Fuzzy Rule Induction

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

On the Effects of Data Scale on UI Control Agents

Nested Learning: The Illusion of Deep Learning Architectures

Evaluation and Benchmarking of LLM Agents: A Survey

mHC: Manifold-Constrained Hyper-Connections

The Diffusion Duality

A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)

When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions

Soft Adaptive Policy Optimization

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution

Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention

Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation

Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku

Model Hypnosis: Strong control of AI via additive subliminal effects

Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents

SPADE: Self-Play in Adaptive Synthetic Executable Environments

SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL

Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models

CAPO: Constraint-Aware Prompt Optimization for LLM Agents

Optimal Lower Bounds for Networked Information Aggregation

Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads

Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics

AI-Assisted Discovery and Construction of a Counterexample to the Convergence of Three-Block ADMM with the Identity Matrix as its Third Constraint Block

Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions

Musical Mirrors: The LLM as Sounding Board in Songwriting

Jais 2: A Family of Arabic-Centric Open Large Language Models

Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions

Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning

PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization

G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection

Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget

Length Penalties Make Chain-of-Thought Less Monitorable

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

Confidence-Aware Tool Orchestration for Robust Video Understanding

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

OpenThoughts-Agent: Data Recipes for Agentic Models

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Can Generalist Agents Automate Data Curation?

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts

A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation

Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Latent Preference Modeling for Cross-Session Personalized Tool Calling