{"total":203,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"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":"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":"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":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105,"area":null},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"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":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68,"area":null},{"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":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"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":"2607.07946","title":"DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks","created":"2026-07-08","cited_by_count":49,"area":"agents"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34,"area":"agents"},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2602.11103","title":"GameDevBench: Evaluating Agentic Capabilities Through Game Development","created":"2026-02-11","cited_by_count":28,"area":"agents"},{"id":"2506.07636","title":"SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling","created":"2025-06-09","cited_by_count":26,"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":"2506.03011","title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","created":"2025-06-03","cited_by_count":25,"area":"agents"},{"id":"2502.07942","title":"Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs","created":"2025-02-11","cited_by_count":24,"area":"agents"},{"id":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2602.23166","title":"AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios","created":"2026-02-26","cited_by_count":23,"area":null},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22,"area":"agents"},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21,"area":"agents"},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"area":null},{"id":"2606.07297","title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","created":"2026-06-05","cited_by_count":21,"area":"agents"},{"id":"2512.14895","title":"Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections","created":"2025-12-16","cited_by_count":19,"area":"agents"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"area":"alignment"},{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"id":"2605.09423","title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","created":"2026-05-10","cited_by_count":17,"area":"agents"},{"id":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16,"area":null},{"id":"2512.10218","title":"Does SWE-Bench-Verified Test Agent Ability or Model Memory?","created":"2025-12-11","cited_by_count":16,"area":"agents"},{"id":"2603.26648","title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","created":"2026-03-27","cited_by_count":16,"area":"agents"},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"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":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"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":"2512.02624","title":"PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding","created":"2025-12-02","cited_by_count":14,"area":"lr"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"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":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2602.09540","title":"SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?","created":"2026-02-10","cited_by_count":12,"area":"agents"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2510.24397","title":"APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"area":"agents"},{"id":"2512.03042","title":"PPTArena: A Benchmark for PowerPoint Editing","created":"2025-12-02","cited_by_count":11,"area":null},{"id":"2512.04329","title":"A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks","created":"2025-12-03","cited_by_count":11,"area":"rag"},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"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":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2505.20749","title":"Can Agents Fix Agent Issues?","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2507.15003","title":"The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering","created":"2025-07-20","cited_by_count":9,"area":"agents"},{"id":"2601.07526","title":"MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era","created":"2026-01-12","cited_by_count":9,"area":"agents"},{"id":"2502.06994","title":"SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering","created":"2025-02-10","cited_by_count":8,"area":"agents"},{"id":"2603.02668","title":"SorryDB: Can AI Provers Complete Real-World Lean Theorems?","created":"2026-03-03","cited_by_count":8,"area":null},{"id":"2603.21972","title":"Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2501.13699","title":"DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2602.01465","title":"Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering","created":"2026-02-01","cited_by_count":7,"area":"agents"},{"id":"2605.14415","title":"SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades","created":"2026-05-14","cited_by_count":7,"area":"agents"},{"id":"2506.02387","title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","created":"2025-06-03","cited_by_count":6,"area":"mllm"},{"id":"2510.25744","title":"Completion $\\neq$ Collaboration: Scaling Collaborative Effort with Agents","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2603.01048","title":"RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair","created":"2026-03-01","cited_by_count":6,"area":null},{"id":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"id":"2604.26275","title":"Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering","created":"2026-04-29","cited_by_count":6,"area":"lr"},{"id":"2605.11633","title":"Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations","created":"2026-05-12","cited_by_count":6,"area":"lr"},{"id":"2606.10106","title":"What makes a harness a harness: necessary and sufficient conditions for an agent harness","created":"2026-06-08","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":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null}],"next_cursor":"100"}