{"total":344,"rows":[{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2603.21687","title":"MIRAGE: The Illusion of Visual Understanding","created":"2026-03-23","cited_by_count":65,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2605.05185","title":"OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents","created":"2026-05-06","cited_by_count":21,"area":null},{"id":"2604.13940","title":"AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot","created":"2026-04-15","cited_by_count":19,"area":null},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2601.18184","title":"VIBEVOICE-ASR Technical Report","created":"2026-01-26","cited_by_count":16,"area":null},{"id":"2604.01707","title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","created":"2026-04-02","cited_by_count":12,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2603.06183","title":"CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2601.22964","title":"EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2604.09855","title":"Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards","created":"2026-04-10","cited_by_count":7,"area":null},{"id":"2605.23559","title":"PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA","created":"2026-05-22","cited_by_count":7,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2606.12087","title":"FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents","created":"2026-06-10","cited_by_count":7,"area":null},{"id":"2603.18660","title":"Multimodal Model for Computational Pathology:Representation Learning and Image Compression","created":"2026-03-19","cited_by_count":6,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2605.13829","title":"Negation Neglect: When models fail to learn negations in training","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2606.00095","title":"Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.06462","title":"Benchmark Everything Everywhere All at Once","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2601.19924","title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2602.07549","title":"When Is Enough Not Enough? Illusory Completion in Search Agents","created":"2026-02-07","cited_by_count":5,"area":null},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2603.04737","title":"Interactive Benchmarks","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2603.12664","title":"From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space","created":"2026-03-13","cited_by_count":5,"area":null},{"id":"2604.11969","title":"Narrative-Driven Paper-to-Slide Generation via ArcDeck","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2605.03723","title":"Segmenting Human-LLM Co-authored Text via Change Point Detection","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2605.07141","title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2605.11960","title":"Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters","created":"2026-05-12","cited_by_count":5,"area":null},{"id":"2607.00711","title":"ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2604.00002","title":"Benchmark for Assessing Olfactory Perception of Large Language Models","created":"2026-03-08","cited_by_count":4,"area":null},{"id":"2604.03799","title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","created":"2026-04-04","cited_by_count":4,"area":null},{"id":"2604.07650","title":"A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2604.14624","title":"Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2605.22104","title":"OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2602.01075","title":"ConvexBench: Can LLMs Recognize Convex Functions?","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2602.10346","title":"Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2602.10473","title":"Why Human Guidance Matters in Collaborative Vibe Coding","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2602.12996","title":"Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2603.02138","title":"OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2603.04349","title":"FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.09740","title":"Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.18014","title":"Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2603.28086","title":"MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2603.29045","title":"Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2605.01822","title":"Molecular Representations for Large Language Models","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2605.09778","title":"Nectar: Neural Estimation of Cached-Token Attention via Regression","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2605.21713","title":"Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.27472","title":"AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2606.11702","title":"MedCTA: A Benchmark for Clinical Tool Agents","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2606.17832","title":"From Drift to Coherence: Stabilizing Beliefs in LLMs","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2606.24893","title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.26615","title":"TaskTok: Delving into Task Tokens for Task-driven Image Restoration","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2608.05102","title":"ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2608.31119","title":"PaperGym: Rubric-Centered Evolution for Research-Plan Generation","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2609.10413","title":"Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs","created":"2026-09-09","cited_by_count":3,"area":null},{"id":"2601.22039","title":"Understanding Multimodal Complementarity for Single-Frame Action Anticipation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2601.22365","title":"Towards Solving the Gilbert-Pollak Conjecture via Large Language Models","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.09882","title":"Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.16307","title":"NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.16822","title":"Surg$\\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.18652","title":"Beyond String Matching: Semantic Evaluation of PDF Table Extraction","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2603.19195","title":"How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2603.27183","title":"Communicating about Space: Language-Mediated Spatial Integration Across Partial Views","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2603.29630","title":"BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2603.29846","title":"SNEAK: Evaluating Strategic Communication and Information Leakage in Large Language Models","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.00677","title":"CL-VISTA: Benchmarking Continual Learning in Video Large Language Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.04468","title":"What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2604.26923","title":"ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2605.05927","title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.08887","title":"Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.10820","title":"MaD Physics: Evaluating information seeking under constraints in physical environments","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.16403","title":"When Vision Speaks for Sound","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.17007","title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2605.17448","title":"Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback","created":"2026-05-17","cited_by_count":2,"area":null}],"next_cursor":"100"}