{"total":111,"rows":[{"id":"2605.23904","title":"SkillOpt: Executive Strategy for Self-Evolving Agent Skills","created":"2026-05-22","cited_by_count":148,"area":"agents"},{"id":"2508.14040","title":"ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents","created":"2025-08-19","cited_by_count":50,"area":"lr"},{"id":"2605.27760","title":"SkillGrad: Optimizing Agent Skills Like Gradient Descent","created":"2026-05-26","cited_by_count":26,"area":"agents"},{"id":"2605.23899","title":"From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills","created":"2026-05-22","cited_by_count":22,"area":null},{"id":"2607.03451","title":"SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe","created":"2026-07-03","cited_by_count":20,"area":"agents"},{"id":"2412.04272","title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","created":"2024-12-05","cited_by_count":14,"area":"lr"},{"id":"2506.05587","title":"MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2412.11711","title":"MiMoTable: A Multi-scale Spreadsheet Benchmark with Meta Operations for Table Reasoning","created":"2024-12-16","cited_by_count":13,"area":"lr"},{"id":"2608.19880","title":"EnvHarness: Awakening Static Worlds for Agent Learning","created":"2026-08-20","cited_by_count":13,"area":"agents"},{"id":"2506.13405","title":"RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2606.10546","title":"SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement","created":"2026-06-09","cited_by_count":12,"area":"agents"},{"id":"2608.27454","title":"WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution","created":"2026-08-27","cited_by_count":12,"area":null},{"id":"2512.03042","title":"PPTArena: A Benchmark for PowerPoint Editing","created":"2025-12-02","cited_by_count":11,"area":null},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2606.29955","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","created":"2026-06-29","cited_by_count":11,"area":"agents"},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2605.16986","title":"Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents","created":"2026-05-16","cited_by_count":10,"area":"lr"},{"id":"2609.00829","title":"HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution","created":"2026-09-01","cited_by_count":9,"area":null},{"id":"2510.19247","title":"SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets","created":"2025-10-22","cited_by_count":8,"area":"lr"},{"id":"2606.11435","title":"Agent Skill Evaluation and Evolution: Frameworks and Benchmarks","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2606.13317","title":"SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents","created":"2026-06-11","cited_by_count":7,"area":"agents"},{"id":"2608.02636","title":"Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds","created":"2026-07-31","cited_by_count":7,"area":"agents"},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2601.08741","title":"From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding","created":"2026-01-13","cited_by_count":6,"area":"lr"},{"id":"2505.15874","title":"Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2508.19813","title":"T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables","created":"2025-08-27","cited_by_count":5,"area":"lr"},{"id":"2601.22758","title":"AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2607.22520","title":"The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents","created":"2026-07-24","cited_by_count":5,"area":"agents"},{"id":"2609.24974","title":"Harness-Zero: Harness Distillation via Agent-as-Harness","created":"2026-09-21","cited_by_count":5,"area":"agents"},{"id":"2508.01556","title":"Empowering Tabular Data Preparation with Language Models: Why and How?","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2604.23853","title":"ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation","created":"2026-04-26","cited_by_count":4,"area":"agents"},{"id":"2605.22664","title":"MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance","created":"2026-05-21","cited_by_count":4,"area":"agents"},{"id":"2606.03203","title":"MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2607.25560","title":"Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2608.11079","title":"SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2502.07132","title":"Interactive Data Harmonization with LLM Agents: Opportunities and Challenges","created":"2025-02-10","cited_by_count":3,"area":"agents"},{"id":"2504.20406","title":"Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2506.12339","title":"SheetMind: Actions Set Accuracy, Agents Set the Failure Mode","created":"2025-06-14","cited_by_count":3,"area":"agents"},{"id":"2509.22983","title":"Same Content, Different Representations: A Controlled Study for Table QA","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.13835","title":"ConDABench: Interactive Evaluation of Language Models for Data Analysis","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2511.20297","title":"Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge","created":"2025-11-25","cited_by_count":3,"area":"agents"},{"id":"2605.08687","title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2607.28048","title":"SKILL-KD: Contrastive Skill Distillation for LLM Agents","created":"2026-07-30","cited_by_count":3,"area":"agents"},{"id":"2608.09629","title":"Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?","created":"2026-08-10","cited_by_count":3,"area":"agents"},{"id":"2609.08944","title":"SkillAdam: Stable and Efficient Skill Evolution for Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2605.30907","title":"BlueFin: Benchmarking LLM Agents on Financial Spreadsheets","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2606.17321","title":"ProCUA-SFT Technical Report","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2607.20999","title":"Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills","created":"2026-07-23","cited_by_count":2,"area":"agents"},{"id":"2607.27155","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.01678","title":"Progressive Agent Skill Generation via Reinforcement Learning","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2608.03764","title":"GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.05563","title":"When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems","created":"2026-08-06","cited_by_count":2,"area":"agents"},{"id":"2608.26195","title":"Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2409.07653","title":"STAND: Self-Aware Precondition Induction for Interactive Task Learning","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2601.07280","title":"ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2604.20070","title":"Auditing and Controlling AI Agent Actions in Spreadsheets","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.17617","title":"GraphMind: From Operational Traces to Self-Evolving Workflow Automation","created":"2026-05-17","cited_by_count":1,"area":"synth"},{"id":"2605.21347","title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2607.06008","title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2607.17044","title":"Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent","created":"2026-07-19","cited_by_count":1,"area":null},{"id":"2607.19865","title":"DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.07056","title":"BONSAI: Evolvability-Guided Tree Search over Skills","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.26546","title":"DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.10494","title":"IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2609.11682","title":"COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.39148","title":"Do Self-Evolving Skills Generalize to Held-Out Tasks?","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2610.01256","title":"DeFA: Dependency-Guided Failure Attribution for LLM Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2610.02762","title":"Dynamic LLM Routers are Often Misguided","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2510.24937","title":"OrchVis: Hierarchical Multi-Agent Orchestration for Human Oversight","created":"2025-10-28","cited_by_count":0,"area":"agents"},{"id":"2605.22642","title":"Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"id":"2606.13802","title":"A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.01245","title":"Office Comprehension Benchmark","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.18438","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.23124","title":"AgentOmnia: Scaling Agentic Models for Full-Scenario Applications","created":"2026-07-25","cited_by_count":0,"area":"agents"},{"id":"2607.28777","title":"Self-Supervised Skill Optimization","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.00018","title":"CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.07885","title":"Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.08303","title":"Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2608.08677","title":"Branch2Skill: Efficient Skill Evolution Through Reasoning Trees","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.12428","title":"MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.16544","title":"VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.24145","title":"TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.30785","title":"SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00367","title":"Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2609.07603","title":"FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.21749","title":"GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.26261","title":"Coding Agents are Strong Prompt Optimizers","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2609.30123","title":"HEXIS: Compiling Agent Skills into Extended Finite State Machines","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30604","title":"The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32731","title":"SkillVine: Agent Skill Evolution via Branching Exploration","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32886","title":"StraTune: Adaptive Selection of Revision Operators for Self-Evolving LLM Skills","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2609.34397","title":"SkillFocus: Evolving Agent Skills via Capability Decomposition","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34469","title":"The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36043","title":"SAGE: A Statistical Acceptance Gate for Self-Evolving Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37128","title":"SkillCome: Group Contrast Skill Optimization with Dual Memory","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38024","title":"Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation","created":"2026-09-29","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}