{"total":105,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"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":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142,"area":"agents"},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2505.03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch","created":"2025-05-06","cited_by_count":72,"area":"agents"},{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65,"area":"agents"},{"id":"2505.19955","title":"MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research","created":"2025-05-26","cited_by_count":64,"area":"agents"},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35,"area":null},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2507.16280","title":"ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry","created":"2025-07-22","cited_by_count":32,"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":"2601.11044","title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","created":"2026-01-16","cited_by_count":28,"area":"agents"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2506.10128","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs","created":"2025-06-11","cited_by_count":25,"area":"lr"},{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25,"area":"agents"},{"id":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2507.05269","title":"CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","created":"2025-07-03","cited_by_count":24,"area":"lr"},{"id":"2502.13767","title":"Agentic AI Software Engineers: Programming with Trust","created":"2025-02-19","cited_by_count":20,"area":"agents"},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2508.14104","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation","created":"2025-08-17","cited_by_count":12,"area":null},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2505.20749","title":"Can Agents Fix Agent Issues?","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2603.04601","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2509.25189","title":"InfoAgent: Advancing Autonomous Information-Seeking Agents","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7,"area":"agents"},{"id":"2606.03829","title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2507.18755","title":"Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback","created":"2025-07-24","cited_by_count":6,"area":"agents"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2606.30182","title":"MirrorCode: AI can rebuild entire programs from behavior alone","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2608.11888","title":"Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2506.00172","title":"Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2507.09866","title":"Turning the Tide: Repository-based Code Reflection","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2609.08149","title":"SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents","created":"2026-09-08","cited_by_count":5,"area":"agents"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2509.16749","title":"Evaluating LLM Generated Detection Rules in Cybersecurity","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2604.24023","title":"ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services","created":"2026-04-27","cited_by_count":4,"area":null},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2603.22999","title":"PaperVoyager : Building Interactive Web with Visual Language Models","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.05912","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.05955","title":"Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution","created":"2026-04-07","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"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":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2505.19489","title":"Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults","created":"2025-05-26","cited_by_count":2,"area":"agents"},{"id":"2510.12409","title":"PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2511.12306","title":"UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI","created":"2025-11-15","cited_by_count":2,"area":"agents"},{"id":"2511.20216","title":"CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2605.17439","title":"DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents","created":"2026-05-17","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":"2608.26195","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":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2510.05441","title":"UnitTenX: Generating Tests for Legacy Packages with AI Agents Powered by Formal Verification","created":"2025-10-06","cited_by_count":1,"area":"agents"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2605.14790","title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2608.06329","title":"Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.11341","title":"Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2503.04828","title":"Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.23053","title":"A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2510.19423","title":"ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2512.02567","title":"Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.04920","title":"Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.11518","title":"How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.13209","title":"LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.02244","title":"The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2605.02661","title":"AcademiClaw: When Students Set Challenges for AI Agents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.11166","title":"Flaws in the LLM Automation Narrative","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.02684","title":"Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.29560","title":"Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.25591","title":"Evaluating Coding Agents on Kernel Exploit Generation","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32600","title":"CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":"100"}