{"total":167,"rows":[{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815,"area":null},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647,"area":null},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224,"area":null},{"id":"2510.04374","title":"GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks","created":"2025-10-05","cited_by_count":158,"area":null},{"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":"2505.09598","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","created":"2025-05-14","cited_by_count":76,"area":null},{"id":"2507.05241","title":"SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47,"area":null},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34,"area":null},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2503.21821","title":"Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving","created":"2025-03-26","cited_by_count":31,"area":null},{"id":"2606.05405","title":"Agents' Last Exam","created":"2026-06-03","cited_by_count":31,"area":null},{"id":"2508.04183","title":"Characterizing Deep Research: A Benchmark and Formal Definition","created":"2025-08-06","cited_by_count":30,"area":null},{"id":"2507.14632","title":"BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM","created":"2025-07-19","cited_by_count":29,"area":null},{"id":"2506.10406","title":"PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier","created":"2025-06-12","cited_by_count":28,"area":null},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20,"area":null},{"id":"2508.13180","title":"Search-Time Data Contamination","created":"2025-08-12","cited_by_count":19,"area":null},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2511.16931","title":"OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists","created":"2025-11-21","cited_by_count":18,"area":null},{"id":"2511.22173","title":"RefineBench: Evaluating Refinement Capability of Language Models via Checklists","created":"2025-11-27","cited_by_count":15,"area":null},{"id":"2505.23522","title":"OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data","created":"2025-05-29","cited_by_count":14,"area":null},{"id":"2602.11685","title":"DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2602.13964","title":"HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam","created":"2026-02-15","cited_by_count":12,"area":null},{"id":"2602.17594","title":"AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2505.24477","title":"Evaluating Gemini in an arena for learning","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2508.02621","title":"HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2510.02663","title":"TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models","created":"2025-10-03","cited_by_count":11,"area":null},{"id":"2510.26384","title":"Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings","created":"2025-10-30","cited_by_count":11,"area":null},{"id":"2601.19532","title":"Benchmarks Saturate When The Model Gets Smarter Than The Judge","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2502.07577","title":"Automated Capability Discovery via Foundation Model Self-Exploration","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2504.02767","title":"How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2510.08521","title":"FlowSearch: Advancing deep research with dynamic structured knowledge flow","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2605.13171","title":"Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2511.22978","title":"ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?","created":"2025-11-28","cited_by_count":9,"area":null},{"id":"2606.04455","title":"The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2511.18743","title":"RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context","created":"2025-11-24","cited_by_count":8,"area":null},{"id":"2512.08868","title":"EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2603.23522","title":"Qworld: Question-Specific Evaluation Criteria for LLMs","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2604.06802","title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2505.17139","title":"EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2606.17930","title":"How Inference Compute Shapes Frontier LLM Evaluation","created":"2026-06-16","cited_by_count":7,"area":null},{"id":"2503.23361","title":"Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base","created":"2025-03-30","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":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2505.23851","title":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2508.00830","title":"BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2601.18226","title":"Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2512.01224","title":"CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.14220","title":"Estimating problem difficulty without ground truth using Large Language Model comparisons","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2605.15000","title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.25133","title":"Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2505.17228","title":"Automated Capability Evaluation of Foundation Models","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2507.13337","title":"FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2512.19753","title":"QMBench: A Research Level Benchmark for Quantum Materials Research","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2601.19578","title":"Yunque DeepResearch Technical Report","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2604.04898","title":"QED-Nano: Teaching a Tiny Model to Prove Hard Theorems","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2604.15664","title":"Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2606.12291","title":"Measuring Epistemic Resilience of LLMs Under Misleading Medical Context","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2606.15300","title":"CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?","created":"2026-06-13","cited_by_count":3,"area":null},{"id":"2606.23196","title":"When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2504.02793","title":"A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.00741","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.02058","title":"Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2507.15576","title":"Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2510.20279","title":"ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2510.20784","title":"A Coherence-Based Measure of AGI","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2510.25979","title":"AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2511.16997","title":"MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2601.11560","title":"DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2603.04857","title":"FireBench: Evaluating Instruction Following in Enterprise and API-Driven LLM Applications","created":"2026-03-05","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":"2604.02368","title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.11209","title":"Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2608.19437","title":"Are LLMs becoming similarly creative? Evidence from three years of models","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2608.29685","title":"Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2502.15226","title":"Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2503.15182","title":"Foundation models may exhibit staged progression in novel CBRN threat disclosure","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2506.00612","title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2507.21695","title":"Towards a Large Physics Benchmark","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2511.18298","title":"Cross-Disciplinary Knowledge Retrieval and Synthesis: A Compound AI Architecture for Scientific Discovery","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2511.21591","title":"On the Limits of Innate Planning in Large Language Models","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.16942","title":"SourceBench: Can AI Answers Reference Quality Web Sources?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.09836","title":"COMPOSITE-Stem","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.19877","title":"Super Apriel: One Checkpoint, Many Speeds","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.07268","title":"From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.08614","title":"DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.18663","title":"GIM: Evaluating models via tasks that integrate multiple cognitive domains","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.21482","title":"DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.26937","title":"Beyond Questions: Evaluating the Stated Knowledge of LLMs","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","created":"2026-05-26","cited_by_count":1,"area":null}],"next_cursor":"100"}