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)

781 to 840 of 15,236

SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases
Yawei Sun, Lingling Zhang, Gong Cheng +1
cs.CLcs.AIarXiv:2003.13956v12020
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
Haoyang Hong, Jiajun Yin, Yuan Wang +14
cs.AIarXiv:2511.13288v22025
BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions
Nan Huo, Xiaohan Xu, Jinyang Li +21
cs.AIarXiv:2510.05318v32025
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar +10
cs.AIcs.CLcs.LGarXiv:2509.19736v12025
AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
Hailin Zhong, Shengxin Zhu
cs.SEcs.AIarXiv:2605.13357v12026
Single-stream Policy Optimization
Zhongwen Xu, Zihan Ding
cs.LGcs.AIstat.MLarXiv:2509.13232v22025
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
Zhenjia Xu, Jiajun Wu, Andy Zeng +2
cs.ROcs.AIcs.CVarXiv:1906.03853v22019
A Survey on Efficient Vision-Language-Action Models
Zhaoshu Yu, Bo Wang, Pengpeng Zeng +7
cs.CVcs.AIcs.LGarXiv:2510.24795v22025
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Sicheng Feng, Kaiwen Tuo, Song Wang +3
cs.CVcs.AIarXiv:2510.02240v22025
Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
Runqian Wang, Yilun Du
cs.LGcs.AIcs.CVarXiv:2510.02300v32025
Adam-mini: Use Fewer Learning Rates To Gain More
Yushun Zhang, Congliang Chen, Ziniu Li +6
cs.LGcs.AIarXiv:2406.16793v72024
Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support
Anna Kawakami, Venkatesh Sivaraman, Hao-Fei Cheng +7
cs.HCcs.AIcs.CYarXiv:2204.02310v12022
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Chia-Yu Hung, Navonil Majumder, Haoyuan Deng +7
cs.ROcs.AIarXiv:2511.14659v12025
Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
Peter Chen, Xiaopeng Li, Ziniu Li +3
cs.LGcs.AIcs.CLarXiv:2512.16912v32025
WorldGen: From Text to Traversable and Interactive 3D Worlds
Dilin Wang, Hyunyoung Jung, Tom Monnier +22
cs.CVcs.AIarXiv:2511.16825v12025
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
Cheng Yang, Haiyuan Wan, Yiran Peng +8
cs.CVcs.AIarXiv:2511.15065v22025
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Yuchuan Tian, Yuchen Liang, Shuo Zhang +10
cs.CLcs.AIarXiv:2512.06776v22025
Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training
Luming Yang, Haoxian Liu, Siqing Li +4
cs.MAcs.AIcs.HCarXiv:2609.10939v12026
Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge
Yuanchen Bai, Zijian Ding, Angelique Taylor
cs.AIcs.HCcs.MAarXiv:2609.10724v12026
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA, :, Aaron Blakeman +356
cs.CLcs.AIcs.LGarXiv:2512.20856v12025
Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations
Doreen Jirak, Armeen Saroukanoff, Dirk van Rooy
cs.HCcs.AIarXiv:2609.11805v12026
AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysis
Calvin Yeung, Keisuke Fujii
cs.HCcs.AIarXiv:2609.11224v12026
Thought Communication in Multiagent Collaboration
Yujia Zheng, Zhuokai Zhao, Zijian Li +4
cs.LGcs.AIcs.MAarXiv:2510.20733v12025
Mixture of Horizons in Action Chunking
Dong Jing, Gang Wang, Jiaqi Liu +7
cs.ROcs.AIcs.CVarXiv:2511.19433v22025
How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding
Jeongyeon Kim, John Mitchell
cs.HCcs.AIarXiv:2609.11109v12026
Code2Video: A Code-centric Paradigm for Educational Video Generation
Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou
cs.CVcs.AIcs.CLarXiv:2510.01174v12025
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Xinlei Yu, Chengming Xu, Guibin Zhang +7
cs.CVcs.AIcs.LGarXiv:2511.11007v22025
DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
Shih-Yang Liu, Xin Dong, Ximing Lu +9
cs.LGcs.AIcs.CLarXiv:2510.15110v12025
Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Han Liu, Vivian Lai, Chenhao Tan
cs.AIcs.CYcs.HCarXiv:2101.05303v42021
Multilingual Routing in Mixture-of-Experts
Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz +2
cs.CLcs.AIcs.LGarXiv:2510.04694v22025
Demystifying the Privacy-Utility Trade-off in LLM Interactions
Zhenhua Liu, Zhanxu Xie, Junjie Yu +3
cs.AIcs.CRarXiv:2609.10992v12026
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Yizhang Zhu, Liangwei Wang, Chenyu Yang +22
cs.DBcs.AIarXiv:2510.23587v22025
ToolUniverse: An open platform for democratizing AI scientists
Shanghua Gao, Richard Zhu, Pengwei Sui +8
cs.AIcs.LGarXiv:2509.23426v32025
terms.txt: A Consent and Compensation Protocol for Agentic Web Access
Rajarshi Chowdhury
cs.NIcs.AIcs.CRarXiv:2609.11152v12026
LITA: Language Instructed Temporal-Localization Assistant
De-An Huang, Shijia Liao, Subhashree Radhakrishnan +4
cs.CVcs.AIarXiv:2403.19046v12024
Distinguishing cause from effect using observational data: methods and benchmarks
Joris M. Mooij, Jonas Peters, Dominik Janzing +2
cs.LGcs.AIstat.MLarXiv:1412.3773v32014
QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models
Li Puyin, Tiange Xiang, Ella Mao +5
cs.AIarXiv:2512.19526v12025
Muon Outperforms Adam in Tail-End Associative Memory Learning
Shuche Wang, Fengzhuo Zhang, Jiaxiang Li +6
cs.LGcs.AImath.OCarXiv:2509.26030v22025
On the Pitfalls of Measuring Emergent Communication
Ryan Lowe, Jakob Foerster, Y-Lan Boureau +2
cs.LGcs.AIcs.CLarXiv:1903.05168v12019
Meta-RL Induces Exploration in Language Agents
Yulun Jiang, Liangze Jiang, Damien Teney +2
cs.LGcs.AIarXiv:2512.16848v22025
Paper2Video: Automatic Video Generation from Scientific Papers
Zeyu Zhu, Kevin Qinghong Lin, Mike Zheng Shou
cs.CVcs.AIcs.CLarXiv:2510.05096v22025
MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
Yu Ying Chiu, Michael S. Lee, Rachel Calcott +17
cs.CLcs.AIcs.CYarXiv:2510.16380v22025
LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild
Jiayu Wang, Yifei Ming, Riya Dulepet +7
cs.AIarXiv:2510.14240v52025
Remote Labor Index: Measuring AI Automation of Remote Work
Mantas Mazeika, Alice Gatti, Cristina Menghini +44
cs.LGcs.AIcs.CLarXiv:2510.26787v12025
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
Xiangyuan Xue, Yifan Zhou, Guibin Zhang +7
cs.CLcs.AIarXiv:2510.08529v22025
A theory of multiclass boosting
Indraneel Mukherjee, Robert E. Schapire
stat.MLcs.AIarXiv:1108.2989v12011
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Hansheng Chen, Kai Zhang, Hao Tan +3
cs.LGcs.AIcs.CVarXiv:2510.14974v32025
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
Guy Frankovits, Lior Yasur, Fred M. Grabovski +1
cs.CRcs.AIarXiv:2609.11404v12026
ARE: Scaling Up Agent Environments and Evaluations
Romain Froger, Pierre Andrews, Matteo Bettini +21
cs.AIcs.CLarXiv:2509.17158v22025
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou +11
cs.LGcs.AIcs.CLarXiv:2510.09781v12025
SynthID-Image: Image watermarking at internet scale
Sven Gowal, Rudy Bunel, Florian Stimberg +23
cs.CRcs.AIarXiv:2510.09263v12025
No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers
Zehua Zhang, Jie Hu, Pratham Hegde +13
cs.CRcs.AIarXiv:2609.10854v12026
Are We on the Right Way to Assessing LLM-as-a-Judge?
Yuanning Feng, Sinan Wang, Zhengxiang Cheng +2
cs.CLcs.AIarXiv:2512.16041v12025
A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation
Dinghan Shen, Mingzhi Zheng, Yelong Shen +2
cs.CLcs.AIarXiv:2009.13818v22020
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros +3
cs.CRcs.AIarXiv:2609.10707v12026
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
Zheng Ding, Weirui Ye
cs.LGcs.AIcs.CVarXiv:2512.08153v12025
Responsible Autonomy
Virginia Dignum
cs.AIarXiv:1706.02513v12017
SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
Qibai Chen, Zeming Liu
cs.AIcs.SEarXiv:2609.11180v12026
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
Shenghan Zheng, Zonglin Di, Yimin Liu +19
cs.CRcs.AIcs.SEarXiv:2609.11028v12026
Summaries:한국어
Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents
Susheel Suresh, Hazel Mak, Sahil Bhatnagar +2
cs.AIcs.SEarXiv:2609.11060v12026

Artificial Intelligence

SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases

Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

Single-stream Policy Optimization

DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions

A Survey on Efficient Vision-Language-Action Models

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

Adam-mini: Use Fewer Learning Rates To Gain More

Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

WorldGen: From Text to Traversable and Interactive 3D Worlds

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training

Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge

NVIDIA Nemotron 3: Efficient and Open Intelligence

Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations

AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysis

Thought Communication in Multiagent Collaboration

Mixture of Horizons in Action Chunking

How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding

Code2Video: A Code-centric Paradigm for Educational Video Generation

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making

Multilingual Routing in Mixture-of-Experts

Demystifying the Privacy-Utility Trade-off in LLM Interactions

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

ToolUniverse: An open platform for democratizing AI scientists

terms.txt: A Consent and Compensation Protocol for Agentic Web Access

LITA: Language Instructed Temporal-Localization Assistant

Distinguishing cause from effect using observational data: methods and benchmarks

QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models

Muon Outperforms Adam in Tail-End Associative Memory Learning

On the Pitfalls of Measuring Emergent Communication

Meta-RL Induces Exploration in Language Agents

Paper2Video: Automatic Video Generation from Scientific Papers

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Remote Labor Index: Measuring AI Automation of Remote Work

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

A theory of multiclass boosting

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks

ARE: Scaling Up Agent Environments and Evaluations

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

SynthID-Image: Image watermarking at internet scale

No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Are We on the Right Way to Assessing LLM-as-a-Judge?

A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Responsible Autonomy

SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents