{"total":262,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"area":"lr"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2502.00334","title":"UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models","created":"2025-02-01","cited_by_count":48,"area":"lr"},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37,"area":"safety"},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32,"area":"lr"},{"id":"2502.16906","title":"AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models","created":"2025-02-24","cited_by_count":31,"area":"lr"},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2503.04149","title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination","created":"2025-03-06","cited_by_count":23,"area":"lr"},{"id":"2509.26062","title":"DyFlow: Dynamic Workflow Framework for Agentic Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2409.12136","title":"GRIN: GRadient-INformed MoE","created":"2024-09-18","cited_by_count":17,"area":"moe"},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2412.14140","title":"GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2509.26553","title":"Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling","created":"2025-09-30","cited_by_count":13,"area":"agents"},{"id":"2603.07980","title":"\\$OneMillion-Bench: How Far are Language Agents from Human Experts?","created":"2026-03-09","cited_by_count":13,"area":"agents"},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2504.06564","title":"Thinking Out Loud: Do Reasoning Models Know When They're Right?","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2508.10026","title":"SABER: Switchable and Balanced Training for Efficient LLM Reasoning","created":"2025-08-08","cited_by_count":12,"area":"lr"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11,"area":"lr"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"id":"2507.21503","title":"MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions","created":"2025-07-29","cited_by_count":11,"area":"mllm"},{"id":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2606.06712","title":"Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation","created":"2026-06-04","cited_by_count":11,"area":"diffusion"},{"id":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2511.00162","title":"ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2602.12966","title":"ProbeLLM: Automating Principled Diagnosis of LLM Failures","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2506.12119","title":"Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource","created":"2025-06-13","cited_by_count":8,"area":"moe"},{"id":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2509.22887","title":"Infusing Theory of Mind into Socially Intelligent LLM Agents","created":"2025-09-26","cited_by_count":8,"area":"agents"},{"id":"2510.07575","title":"Benchmarking is Broken -- Don't Let AI be its Own Judge","created":"2025-10-08","cited_by_count":8,"area":null},{"id":"2601.15279","title":"MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs","created":"2026-01-21","cited_by_count":8,"area":"lr"},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2509.14221","title":"GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing","created":"2025-09-17","cited_by_count":7,"area":null},{"id":"2601.07606","title":"Proof of Time: A Benchmark for Evaluating Scientific Idea Judgments","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2601.10504","title":"DR-Arena: an Automated Evaluation Framework for Deep Research Agents","created":"2026-01-15","cited_by_count":6,"area":"agents"},{"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":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2512.00417","title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","created":"2025-11-29","cited_by_count":5,"area":"agents"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2603.20807","title":"BenchBench: Benchmarking Automated Benchmark Generation","created":"2026-03-21","cited_by_count":5,"area":null},{"id":"2605.02209","title":"Submodular Benchmark Selection","created":"2026-05-04","cited_by_count":5,"area":null},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2512.04416","title":"DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2512.20823","title":"NotSoTiny: A Large, Living Benchmark for RTL Code Generation","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2601.05039","title":"FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2601.05073","title":"Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2602.16747","title":"LiveClin: A Live Clinical Benchmark without Leakage","created":"2026-02-18","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":"2505.23001","title":"DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors","created":"2025-05-29","cited_by_count":3,"area":"safety"},{"id":"2510.21513","title":"Wisdom and Delusion of LLM Ensembles for Code Generation and Repair","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2512.21231","title":"MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models","created":"2025-12-24","cited_by_count":3,"area":"lr"},{"id":"2601.02941","title":"SastBench: A Benchmark for Testing Agentic SAST Triage","created":"2026-01-06","cited_by_count":3,"area":"agents"},{"id":"2601.09876","title":"Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2601.17312","title":"Meta-Judging with Large Language Models: Concepts, Methods, and Challenges","created":"2026-01-24","cited_by_count":3,"area":null},{"id":"2602.05305","title":"FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2603.15699","title":"This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.03244","title":"AI Evaluation Should Require Standardized Item-Level Data Releases","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2605.09826","title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.17574","title":"DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"area":"agents"},{"id":"2411.09492","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2412.15177","title":"Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying","created":"2024-12-19","cited_by_count":2,"area":"lr"},{"id":"2505.03678","title":"Graph Drawing for LLMs: An Empirical Evaluation","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.14913","title":"Budget-aware Test-time Scaling via Discriminative Verification","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2510.17013","title":"DiscoTrack: A Multilingual LLM Benchmark for Discourse Tracking","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","cited_by_count":2,"area":null}],"next_cursor":"100"}