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)

27,361 to 27,417 of 27,417

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
Neeraj Kumar Singh Beshane
cs.CRcs.AIarXiv:2608.17176v12026
Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot
Hui Mao
cs.CEcs.AIarXiv:2608.16795v12026
What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
Xiaonan Xu, Wenjing Wu
cs.SEcs.AIcs.CLarXiv:2608.17719v12026
Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level
Hannah Cha
cs.CYcs.AIcs.HCarXiv:2608.14692v12026
Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems
Patrick Emami, Sameera Horawalavithana, Truc Nguyen +11
cs.AIcs.HCarXiv:2608.14667v12026
WIP: LLM Odyssey: A Game-Based Platform for Teaching LLM Engineering Concepts
Priyamvada Tripathi
cs.CYcs.AIarXiv:2608.16924v12026
ARGUS: Attention-Guided Transformers for Scalable Person Identification Using Wi-Fi Telemetry
Nayan Sanjay Bhatia, Pranay Kocheta, Yuhan Li +1
cs.LGcs.AIcs.CVarXiv:2608.14670v12026
Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task
Alexandru-Stefan Morosanu, Valerian Cecan, Stefan-Daniel Achirei +1
cs.SDcs.AIcs.LGarXiv:2608.14916v12026
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
Yatai Ji, An-Chieh Cheng, Yang Fu +13
cs.CVcs.AIarXiv:2606.17539v12026
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Bobo Li, Rui Wu, Zibo Ji +5
cs.CLcs.AIcs.CYarXiv:2604.19548v12026
MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure
Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil +1
cs.LGcs.AIcs.HCarXiv:2608.17823v12026
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh +3
cs.CLcs.AIarXiv:2605.18565v22026
A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems
Titu Ranjan Sarker, Muhammed Jawaad Zulqernine, Ling Yue +3
cs.AIarXiv:2606.00138v12026
LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents
Yuefeng Zou, Yichen Lu, Jingxiao Yang +5
cs.AIarXiv:2608.15064v12026
Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis
Ummara Mumtaz, Summaya Mumtaz
q-fin.STcs.AIcs.CLarXiv:2311.06273v12023
Afterlife Delegation Protocol: Speculative Design of Self-Sovereign Agents that Outlive Their Principals
Botao Amber Hu, Iris Long
cs.CYcs.AIarXiv:2608.15405v12026
TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions
Md Fazley Rafy
cs.AIcs.CRarXiv:2608.15391v12026
Memory Is Communication: The Frontier Between Remembering and Signaling
Yashar Talebirad, Eden Redman, Ali Parsaee +1
cs.AIcs.CLcs.ITarXiv:2608.17053v12026
No Gaussian Required: Contrastive Inverse Dynamics for JEPA World Models
Jack Boylan, Chris Hokamp
cs.LGcs.AIarXiv:2608.17542v12026
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Jiaming Wang, Ziteng Feng, Jiangtao Wu +8
cs.AIarXiv:2606.02060v22026
The Role of Feedback Alignment in Self-Distillation
Semih Kara, Oğuzhan Ersoy
cs.AIcs.LGarXiv:2606.11173v12026
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
cs.CLcs.AIarXiv:2605.05662v12026
AutoSR: Automatic Symbolic Regression by Searching Research States
Kejia Zhang, Youran Sun, Xinyu Ren +2
cs.SCcs.AIcs.LGarXiv:2608.16876v12026
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Ye Yuan, Rui Song, Weien Li +12
cs.CLcs.AIcs.MAarXiv:2605.27068v12026
NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models
Yiming Fu, Fangjun Li, Xiujin Liu +7
cs.CVcs.AIarXiv:2608.15425v12026
FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge
Rajat Bhattacharjya, Yoomee Jung, Minwoo Kim +4
cs.DCcs.AIcs.CVarXiv:2608.15410v12026
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
Che Liu, Lichao Ma, Xiangyu Tony Zhang +4
cs.MMcs.AIcs.CVarXiv:2605.12034v22026
Toto 2.0: Time Series Forecasting Enters the Scaling Era
Emaad Khwaja, Chris Lettieri, Gerald Woo +10
cs.LGcs.AIarXiv:2605.20119v22026
The Benchmark Trap: Structures of Power and Injustice in AI Evaluations
Jason Branford, Angelie Kraft
cs.AIcs.CYarXiv:2608.15326v12026
FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making
Pramit Dutta, Jenita Manokaran, Richa Mittal +2
cs.CVcs.AIarXiv:2608.15004v12026
Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization
Tony Alex, Wish Suharitdamrong, Sara Atito +5
cs.SDcs.AIcs.CLarXiv:2608.16539v12026
Audio-Visual Segmentation via Depth-Guided Collaborative Modeling
Zhaojin Fu, Yuyang Hong, Qi Yang +4
cs.CVcs.AIarXiv:2608.16285v12026
Rewrite Once, Validate Anywhere: Producing OWL-Aware SHACL Constraints (Extended Version)
Anouk Oudshoorn, Piotr Gorczyca, Dörthe Arndt
cs.LOcs.AIarXiv:2608.14104v12026
Useful Memories Become Faulty When Continuously Updated by LLMs
Dylan Zhang, Yanshan Lin, Zhengkun Wu +4
cs.AIarXiv:2605.12978v12026
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
Yunfei Zhang, Boyu Feng, Changhua Pei +14
cs.AIcs.SEarXiv:2608.15242v12026
Understanding Cognition-Induced Risks in Agentic AI Systems
Guanchu Wang, Qinuo Li, Mengnan Du +2
cs.AIarXiv:2608.15304v12026
Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions
Qingfang Liu, Qiao Jin, Joe D. Menke +2
cs.IRcs.AIcs.CLarXiv:2608.13786v12026
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Qiuyue Wang, Mingsheng Li, Jian Guan +37
cs.ROcs.AIcs.CLarXiv:2605.30280v22026
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Yifan Yang, Ziyang Gong, Weiquan Huang +12
cs.AIcs.CLarXiv:2605.23904v22026
Towards Automating Scientific Review with Google's Paper Assistant Tool
Rajesh Jayaram, Drew Tyler, David Woodruff +4
cs.LGcs.AIcs.CLarXiv:2606.28277v12026
ReFreeKV: Towards Threshold-Free KV Cache Compression
Xuanfan Ni, Liyan Xu, Chenyang Lyu +6
cs.CLcs.AIcs.LGarXiv:2502.16886v42025
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
Kaiyuan Chen, Shuangyu Xie, Letian Fu +21
cs.ROcs.AIcs.CLarXiv:2607.05369v12026
LightMem-Ego: Your AI Memory for Everyday Life
Yijun Chen, Boyi Xiao, Yixian Zhao +10
cs.CLcs.AIcs.CVarXiv:2607.11487v12026
When Does Muon Help Agentic Reinforcement Learning?
Kai Ruan, Jinghao Lin, Zihe Huang +4
cs.LGcs.AIarXiv:2607.16169v42026
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
Haotian Liang, Mingkang Chen, Yufei Huang +27
cs.AIcs.ROarXiv:2607.14187v12026
Ontology-Grounded Project Memory for Coding Agents
James Adam
cs.AIcs.SEarXiv:2608.13662v12026
Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes
Alexei Odinokov, Rostislav Yavorskiy
cs.ROcs.AIarXiv:2608.14481v12026
A Vocabulary for Multi-Agent Automated Research Systems
Bardiya Akhbari
cs.AIcs.LGcs.MAarXiv:2607.22682v12026
An Exam for Active Observers
Jiarui Zhang, Muzi Tao, Shangshang Wang +3
cs.CVcs.AIcs.CLarXiv:2607.16165v12026
LLMs Don't Pay for the Jump
Paras Balani, Subhrakanta Panda
cs.AIcs.CLarXiv:2608.14397v12026
Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis
Aryan Luthra, Kshitij Jain, Siddharth Arya +2
cs.AIcs.CRcs.LGarXiv:2608.13608v12026
Exploring ESC Winners with Nested Diagrams
Anurag Sharma, Marcel Nöhre, Gerd Stumme
cs.AIarXiv:2608.13630v12026
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
Junzhuo Liu, Weiwei Li, Jun Ling +1
cs.AIarXiv:2608.05219v12026
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
Sebastián Andrés Cajas Ordóñez, Agastya Munnangi, Aldo Marzullo +13
cs.AIarXiv:2608.03744v12026
Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT
Pu Zhao, Changdi Yang, Yixiao Chen +4
cs.SEcs.AIcs.ETarXiv:2608.13681v12026
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
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

Artificial Intelligence

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence

Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot

What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations

Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level

Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems

WIP: LLM Odyssey: A Game-Based Platform for Teaching LLM Engineering Concepts

ARGUS: Attention-Guided Transformers for Scalable Person Identification Using Wi-Fi Telemetry

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment

MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure

MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems

LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents

Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis

Afterlife Delegation Protocol: Speculative Design of Self-Sovereign Agents that Outlive Their Principals

TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions

Memory Is Communication: The Frontier Between Remembering and Signaling

No Gaussian Required: Contrastive Inverse Dynamics for JEPA World Models

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

The Role of Feedback Alignment in Self-Distillation

XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

AutoSR: Automatic Symbolic Regression by Searching Research States

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models

FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Toto 2.0: Time Series Forecasting Enters the Scaling Era

The Benchmark Trap: Structures of Power and Injustice in AI Evaluations

FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

Audio-Visual Segmentation via Depth-Guided Collaborative Modeling

Rewrite Once, Validate Anywhere: Producing OWL-Aware SHACL Constraints (Extended Version)

Useful Memories Become Faulty When Continuously Updated by LLMs

LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures

Understanding Cognition-Induced Risks in Agentic AI Systems

Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Towards Automating Scientific Review with Google's Paper Assistant Tool

ReFreeKV: Towards Threshold-Free KV Cache Compression

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

LightMem-Ego: Your AI Memory for Everyday Life

When Does Muon Help Agentic Reinforcement Learning?

RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination

Ontology-Grounded Project Memory for Coding Agents

Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes

A Vocabulary for Multi-Agent Automated Research Systems

An Exam for Active Observers

LLMs Don't Pay for the Jump

Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis

Exploring ESC Winners with Nested Diagrams

When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents

Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems

Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT

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

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