{"total":187,"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":"2603.04448","title":"SkillNet: Create, Evaluate, and Connect AI Skills","created":"2026-02-26","cited_by_count":53,"area":null},{"id":"2604.08523","title":"ClawBench: Can AI Agents Complete Everyday Online Tasks?","created":"2026-04-09","cited_by_count":33,"area":null},{"id":"2603.10910","title":"GLM-OCR Technical Report","created":"2026-03-11","cited_by_count":26,"area":null},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"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":"2603.28458","title":"HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"area":null},{"id":"2606.03461","title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","created":"2026-06-02","cited_by_count":9,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2606.26859","title":"AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems","created":"2026-06-25","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2605.07363","title":"MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference","created":"2026-05-08","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":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2604.12312","title":"CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems","created":"2026-04-14","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":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2605.12882","title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","created":"2026-05-13","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":"2606.01629","title":"Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2606.04511","title":"SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2603.26380","title":"Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.10267","title":"IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2606.04058","title":"Spectral Scaling Laws of Muon","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2606.09365","title":"Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2608.11612","title":"Dion3: Full-Stack Orthogonal Updates","created":"2026-08-12","cited_by_count":4,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.10379","title":"Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness","created":"2026-05-11","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":"2605.27887","title":"PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2606.03070","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.30015","title":"Parametric Skills","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2607.14952","title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2607.24593","title":"PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention","created":"2026-07-27","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":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2603.05026","title":"RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.25382","title":"AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2605.28831","title":"S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2606.09389","title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.01847","title":"FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.01913","title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.04783","title":"RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists","created":"2026-08-05","cited_by_count":2,"area":null},{"id":"2608.08570","title":"FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2608.12679","title":"Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies","created":"2026-08-13","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":"2609.00814","title":"RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2609.11655","title":"Musec: MomentUm SpEctral Clipping for Stable Muon-type Training","created":"2026-09-10","cited_by_count":2,"area":null},{"id":"2602.21257","title":"Structured Prompt Language: Declarative Context Management for LLMs","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.10969","title":"TOSSS: a CVE-based Software Security Benchmark for Large Language Models","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.01621","title":"DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.17561","title":"Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.23668","title":"OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.28046","title":"MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.29157","title":"Parallax: Parameterized Local Linear Attention for Language Modeling","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.30963","title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.03363","title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03852","title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.11998","title":"Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.13782","title":"MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.19857","title":"Large Language Models Do Not Always Need Readable Language","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.20676","title":"Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambiguity","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.23676","title":"Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2606.24162","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.31435","title":"CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.01590","title":"Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.11079","title":"Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.25291","title":"CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.28073","title":"GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.02162","title":"Lossless Tensor Compression as Program Synthesis","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.04339","title":"Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.11919","title":"LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2603.23160","title":"UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.06829","title":"WRAP++: Web discoveRy Amplified Pretraining","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.25806","title":"MAIC-UI: Making Interactive Courseware with Generative UI","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.00072","title":"XekRung Technical Report","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.10442","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.17228","title":"Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.24168","title":"Inference Time Context Sparsity: Illusion or Opportunity?","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.29059","title":"SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.00132","title":"Foundation-Preserving Optimization in Generalized Eigenspace","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.05104","title":"Knowledge Index of Noah's Ark","created":"2026-06-03","cited_by_count":0,"area":null}],"next_cursor":"100"}