Skip to content
AI Atlas
Research

Papers

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

1,050 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong ConversationsarXiv:2609.09664Hyojeong Yu, Hyukhun Koh, Minsung Kim +211 Sept 2026cs.AI—89
Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis AgentsarXiv:2609.09678Yuexin Wu, Vasile Rus11 Sept 2026cs.AI—89
Decision Shifts, Lost Label Functionality, and an Inconclusive Grounding Audit in Correctness-Gated Multi-Teacher DistillationarXiv:2609.09702Xiaofei Feng11 Sept 2026cs.AI—89
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical ReasoningarXiv:2609.09707Yaning Jia, Chunhui Zhang, Wenxuan Xu +211 Sept 2026cs.AI—89
Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online SafetyarXiv:2609.09735Hamed Jelodar, Amir Firouzi, Yen-Wu Lo +211 Sept 2026cs.AI—89
LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal AgentsarXiv:2609.09754Yujin Zhou, Mingxuan Zheng, Chuxue Cao +211 Sept 2026cs.AI—89
Procedural Memory Under Change: Reuse and Interference in Controlled Web TasksarXiv:2609.09774Yanze Cao11 Sept 2026cs.AI—89
Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled RewardarXiv:2609.09776Eshwar Reddy M, Sourav Karmakar11 Sept 2026cs.AI—89
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a ModelarXiv:2609.09815Xing Zhang, Guanghui Wang, Yanwei Cui +211 Sept 2026cs.AI—89
The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM AgentsarXiv:2609.09853Benjamin Gruenbaum, Doron Porat, Assaf Natanzon +211 Sept 2026cs.AI—89
Shifting Relational Paradigms for Affective Computing: Affective Resonance, Vitality Affects, and Vocal Interaction FieldsarXiv:2609.09864Cy Gorman, Yihang Yao11 Sept 2026cs.AI—89
AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI AgentsarXiv:2609.09875Shrey Nag, Sachita, Abhishek Kumar Singh +211 Sept 2026cs.AI—89
Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation FormatarXiv:2609.09882Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua11 Sept 2026cs.AI—89
Decision Transformer for UAV-Mounted RIS-Assisted Dynamic D2D CommunicationsarXiv:2609.09885Yaxuan Liu11 Sept 2026cs.AI—89
Grounded Evaluation and Repair for NL-to-PDDL Problem GenerationarXiv:2609.09898Joana Rosa, Pedro Santos, Valdemar Oliveira +211 Sept 2026cs.AI—89
Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action ModelsarXiv:2609.09925Shengye Dong, Haochen Niu, Hao Liu +211 Sept 2026cs.AI—89
Structural Process Supervision for Latent Chain-of-Thought ReasoningarXiv:2609.09928Yiqi Li, Xu Chen, Chen Ju +211 Sept 2026cs.AI—89
Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial ObservabilityarXiv:2609.10036Arnab Chattopadhayay, Debdipta Halder11 Sept 2026cs.AI—89
OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology NormalizationarXiv:2609.10055Jie Song, Zhichuan Xu, Ziyu Lu +211 Sept 2026cs.AI—89
Reference-Based Bias Detection in LLMs via Relative Representations of Hidden StatesarXiv:2609.10060Marek Jeli\'nski, Jan Dubi\'nski, Maciej Chrabaszcz +111 Sept 2026cs.AI—89
RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition BiasesarXiv:2609.10092Yingqian Wu, Jingcong Liang, Siyuan Wang +211 Sept 2026cs.AI—89
Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather AlertsarXiv:2609.10135Shuai Yan, Yang Xu, Shan He11 Sept 2026cs.AI—89
Kernel-Managed Shared Memory for System-Wide PersonalizationarXiv:2609.10144Ryan Lum, Yongfeng Zhang11 Sept 2026cs.AI—89
Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context LearningarXiv:2609.10177Mingbo Yang, Wenqiang Wang, Zhaolu Kang +211 Sept 2026cs.AI—89
Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool SelectionarXiv:2609.10221Haoyue Liu, Xiaoyu Ma, Ye Chen +211 Sept 2026cs.AI—89
What Should an Agent Forget? Separating What Is Stored from What Is UsedarXiv:2609.10263Yuhang Li, Yuchen Li11 Sept 2026cs.AI—89
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized RewardsarXiv:2609.10315Rui Sun, Zhan Shi, Bing He11 Sept 2026cs.AI—89
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric ReasoningarXiv:2609.10335Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou +211 Sept 2026cs.AI—89
Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking SystemarXiv:2609.10350Alex Leytes11 Sept 2026cs.AI—89
Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMsarXiv:2609.10413Ansuman Mullick, Eray T\"uz\"un11 Sept 2026cs.AI—89
ConvMem: Convolutional Memory for Long-Context ReasoningarXiv:2609.10441Hongming Zhang, Zhaozhen Gu, Fengshuo Bai +211 Sept 2026cs.AI—89
JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task CompositionarXiv:2609.10451Zixiang Chen, Yuheng Lu, Zihao Cheng +211 Sept 2026cs.AI—89
Quantifying Logical Consistency in Transformers via Query-Key AlignmentarXiv:2502.17017Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +211 Sept 2026cs.CL—89
From Plausible to Actionable: A Position on LLM Self-ExplanationsarXiv:2607.15957Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +111 Sept 2026cs.CL—89
Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Evidence DecouplingarXiv:2609.02663Ziquan Liu, Zhewei Zhu, Xuyang Shi11 Sept 2026cs.CV—89
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language ModelsarXiv:2609.03247Syed Ghazanfar Abbas, Dongyan Xu11 Sept 2026cs.CR—89
AgenticGen: Reward-Guided Agentic Video Generation for AdvertisingarXiv:2609.09187Xingyuan Bu, Chengru Song, Hao Zhou +211 Sept 2026cs.CV—89
Reliability-Aware Hybrid-K Ensemble Selection for Cervical Cytology Classification: Integrating Discrimination, Calibration, and Selective PredictionarXiv:2609.09189Nisreen Albzour, Sarah S. Lam11 Sept 2026eess.IV—89
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use AgentsarXiv:2609.09212Zhihao Liu, Hongyu Sun, Zhiyuan Fu +211 Sept 2026cs.CR—89
Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid ModelarXiv:2609.09213Hao Li, Haofei Sun, Lin He11 Sept 2026cs.RO—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.