{"total":110,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2512.10398","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":"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":"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":"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":"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":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"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":"2603.05910","title":"The World Won't Stay Still: Programmable Evolution for Agent Benchmarks","created":"2026-03-06","cited_by_count":5,"area":"agents"},{"id":"2607.02032","title":"PACE: A Proxy for Agentic Capability Evaluation","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2501.19339","title":"PixelWorld: How Far Are We from Perceiving Everything as Pixels?","created":"2025-01-31","cited_by_count":4,"area":"agents"},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"id":"2510.09801","title":"How can we assess human-agent interactions? Case studies in software agent design","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2511.19635","title":"Agint: Agentic Graph Compilation for Software Engineering Agents","created":"2025-11-24","cited_by_count":4,"area":"agents"},{"id":"2605.30690","title":"ElasticMem: Latent Memory as a Learnable Resource for LLM Agents","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2607.28545","title":"ORCA-bench: How Ready Are Language Model Agents for Oncall?","created":"2026-07-30","cited_by_count":4,"area":"agents"},{"id":"2608.11727","title":"Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2608.19653","title":"DeltaML-Bench: Evaluating Machine Learning Agents on Real-World Research Repositories","created":"2026-08-20","cited_by_count":4,"area":"agents"},{"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":"2606.14061","title":"LLM Agents Can See Code Repositories","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2607.05174","title":"AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments","created":"2026-07-06","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":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2609.02783","title":"EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2606.24820","title":"SHERLOC: Structured Diagnostic Localization for Code Repair Agents","created":"2026-06-23","cited_by_count":2,"area":"agents"},{"id":"2608.09072","title":"A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents","created":"2026-08-10","cited_by_count":2,"area":"agents"},{"id":"2609.21562","title":"GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2505.20973","title":"Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2602.13723","title":"Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2603.21630","title":"EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2603.27745","title":"Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits","created":"2026-03-29","cited_by_count":1,"area":"agents"},{"id":"2604.07789","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","created":"2026-04-09","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":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2606.25514","title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","created":"2026-06-24","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2607.28591","title":"Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.04682","title":"Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2609.06780","title":"Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks","created":"2026-09-06","cited_by_count":1,"area":"agents"},{"id":"2609.08318","title":"AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents","created":"2026-09-08","cited_by_count":1,"area":"agents"},{"id":"2609.22000","title":"RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2512.20957","title":"One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents","created":"2025-12-24","cited_by_count":0,"area":"agents"},{"id":"2603.00349","title":"COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems","created":"2026-02-27","cited_by_count":0,"area":"agents"},{"id":"2604.09564","title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","created":"2026-02-14","cited_by_count":0,"area":"agents"},{"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":"2606.05570","title":"TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2607.01929","title":"Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2608.16022","title":"OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development","created":"2026-08-17","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}