Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages.

510 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Role differentiation as ignition of a collective information engine: Structuration in Agent PopulationsarXiv:2609.05442Maximilian Puelma Touzel12 Sept 2026physics.soc-ph—89
Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language ModelsarXiv:2609.09957Chenyu Zhou, Dongdong Ge, Jianghao Lin +212 Sept 2026math.OC—89
A machine-checked proof of the Dong-Yang classification of optimal (n,4) binary codes for BSCsarXiv:2609.10579Shenghao Yang, Yanyan Dong12 Sept 2026math.HO—89
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat MitigationarXiv:2609.10707Anna Gazani, Georgios Koutidis, Grigorios Tsoumakas +212 Sept 2026cs.CR—89
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python CodearXiv:2609.10762Glaucia Melo, Jessica Pourleyli, Maitreyee Das Urmi12 Sept 2026cs.CR—89
Tapes Together Strong: The Co-evolution of Computation and CooperationarXiv:2609.10817Blaise Ag\"uera y Arcas, Blake Aaron Richards, Eyvind Niklasson +212 Sept 2026cs.MA—89
No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP ServersarXiv:2609.10854Adam Doupe, Aditya Maheshbhai Gabani, Chang Zhu +212 Sept 2026cs.CR—89
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMsarXiv:2609.10895Bang Liu, Dekun Wu, Dongqing Zhang +212 Sept 2026cs.RO—89
Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview TrainingarXiv:2609.10939Guanhua Chen, Haoxian Liu, Li Lu +212 Sept 2026cs.MA—89
What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain InsteadarXiv:2609.10962Haseeb Mohammed Afsar12 Sept 2026cs.SE—89
A Mathematical Theory of Pragmatic InformationarXiv:2609.10986Kai Niu, Ping Zhang12 Sept 2026cs.IT—89
DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation AttacksarXiv:2609.11008Liming Fang, Rui Cao, Shaojing Fan +212 Sept 2026cs.CR—89
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation InfrastructurearXiv:2609.11028Alex Yates, Ayush Munot, Bingran You +212 Sept 2026cs.CR—89
Less can be More: What Aspects of Speech Drive End-of-Turn DetectionarXiv:2609.11066Andreas Stolcke, Kadri Hacioglu, Manickavela A +112 Sept 2026eess.AS—89
How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative CodingarXiv:2609.11109Jeongyeon Kim, John Mitchell12 Sept 2026cs.HC—89
terms.txt: A Consent and Compensation Protocol for Agentic Web AccessarXiv:2609.11152Rajarshi Chowdhury12 Sept 2026cs.NI—89
Exploring Second-Order Pattern Recognition in Speaker RecognitionarXiv:2609.11182Mark D. Plumbley, Wenwu Wang, Yanze Xu12 Sept 2026eess.AS—89
X-RACE: XAI-assisted Recurrent neural network Attribution for Channel EstimationarXiv:2609.11211Abdul Karim Gizzini, Yahia Medjahdi12 Sept 2026eess.SP—89
AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data AnalysisarXiv:2609.11224Calvin Yeung, Keisuke Fujii12 Sept 2026cs.HC—89
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon ManipulationarXiv:2609.11308Fengjiao Chen, Renaud Detry, Xuezhi Cao +112 Sept 2026cs.RO—89
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of HarmsarXiv:2609.11373Abhijnan Chakraborty, Abhisek Dash, Ayan Majumdar +212 Sept 2026cs.CY—89
Agent-Integrated Software: Interaction Contracts and Continuous AssurancearXiv:2609.11381Chunrong Fang, Shengcheng Yu, Zhenyu Chen12 Sept 2026cs.SE—89
Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and SignalingarXiv:2609.11391Xinya Guan, Yongchao Martin Ma12 Sept 2026cs.CY—89
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering AttacksarXiv:2609.11404Fred M. Grabovski, Guy Frankovits, Lior Yasur +112 Sept 2026cs.CR—89
Investigating catastrophic forgetting in sound event classificationarXiv:2609.11447Annamaria Mesaros, Riccardo Casciotti12 Sept 2026eess.AS—89
Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Scrape-Off Layer of Stellarator DevicesarXiv:2609.11628A. Alonso (Laboratorio Nacional de Fusi\'on, A. Baciero (Laboratorio Nacional de Fusi\'on, A. Bustos (Departamento de Tecnolog\'ia +212 Sept 2026physics.plasm-ph—89
Warrant TheoryarXiv:2609.11667Khashayar Irani12 Sept 2026cs.LO—89
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM AgentsarXiv:2609.11677Baohan Huang, Cong Zuo, Haibin Zhang +212 Sept 2026cs.SE—89
ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching PoliciesarXiv:2609.11697Jianming Ma, Rongjun Jin, Xiaxi Si +212 Sept 2026cs.RO—89
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNsarXiv:2609.11713Daniel Arum\'i, Elia Mateu-Barriendos, Josep Rius +212 Sept 2026cs.ET—89
Continuous-Time Acoustic Modelling with Neural Controlled Differential EquationsarXiv:2609.11725Anton Ragni, Mattias Cross, Minghui Zhao12 Sept 2026cs.SD—89
Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime OperationsarXiv:2609.11805Armeen Saroukanoff, Dirk van Rooy, Doreen Jirak12 Sept 2026cs.HC—89
GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph ReplayarXiv:2609.11923Boning Li, Longbo Huang12 Sept 2026cs.DC—89
Discovering Temporal Structure: An Overview of Hierarchical Reinforcement LearningarXiv:2506.14045Akhil Bagaria, Doina Precup, George Konidaris +212 Sept 2026cs.AI—89
Timely Clinical Diagnosis through Active Test SelectionarXiv:2510.18988Mihaela van der Schaar, Nicol\'as Astorga, Silas Ruhrberg Est\'evez12 Sept 2026cs.AI—89
Rescaling Confidence: What Scale Design Reveals About LLM MetacognitionarXiv:2603.09309Yuxia Wang, Yuyang Dai12 Sept 2026cs.AI—89
An Agentic Evaluation Framework for AI-Generated Scientific Code in PETScarXiv:2603.15976Barry Smith, Hong Zhang, Junchao Zhang +212 Sept 2026cs.AI—89
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown SchemasarXiv:2603.16448Ai Jian, Eryu Guo, Jiangbo Pei +212 Sept 2026cs.AI—89
How LLMs Follow Instructions: Skillful Coordination, Not a Universal MechanismarXiv:2604.06015Alfio Ferrara, Elisabetta Rocchetti12 Sept 2026cs.AI—89
VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication NoisearXiv:2604.10441Han Ngoc Tran, Kazhal Shafiei, Mehrdad Fazli +212 Sept 2026cs.AI—89

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Each paper page shows the abstract, related models and every source snapshot.