{"total":93,"rows":[{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"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":"2311.09835","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","created":"2023-11-16","cited_by_count":65,"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":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2409.00872","title":"Self-evolving Agents with reflective and memory-augmented abilities","created":"2024-09-01","cited_by_count":52,"area":"agents"},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52,"area":"agents"},{"id":"2502.11705","title":"LLM Agents Making Agent Tools","created":"2025-02-17","cited_by_count":48,"area":"agents"},{"id":"2505.07473","title":"Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks","created":"2025-05-12","cited_by_count":40,"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":"2604.22750","title":"How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks","created":"2026-04-24","cited_by_count":33,"area":"agents"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"area":"agents"},{"id":"2506.17335","title":"LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research","created":"2025-06-19","cited_by_count":29,"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":"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":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","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":"2510.25694","title":"Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents","created":"2025-10-29","cited_by_count":18,"area":"agents"},{"id":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2502.06111","title":"CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories","created":"2025-02-10","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":"2601.10343","title":"OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding","created":"2026-01-15","cited_by_count":15,"area":"agents"},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"id":"2504.21205","title":"SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories","created":"2025-04-29","cited_by_count":14,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"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":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"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":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","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":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2602.08316","title":"SWE Context Bench: A Benchmark for Context Learning in Coding","created":"2026-02-09","cited_by_count":9,"area":"agents"},{"id":"2605.24110","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions","created":"2026-05-22","cited_by_count":9,"area":"agents"},{"id":"2601.16489","title":"EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration","created":"2026-01-23","cited_by_count":8,"area":"agents"},{"id":"2602.22764","title":"Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents","created":"2026-02-26","cited_by_count":8,"area":"agents"},{"id":"2603.00187","title":"ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions","created":"2026-02-27","cited_by_count":8,"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":"2406.07275","title":"DCA-Bench: A Benchmark for Dataset Curation Agents","created":"2024-06-11","cited_by_count":6,"area":"agents"},{"id":"2607.20911","title":"Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2606.00953","title":"When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding","created":"2026-05-31","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":"2607.27250","title":"Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories","created":"2026-07-28","cited_by_count":5,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2604.23069","title":"ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents","created":"2026-04-24","cited_by_count":4,"area":"agents"},{"id":"2605.06068","title":"VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.15846","title":"RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades","created":"2026-05-15","cited_by_count":4,"area":"agents"},{"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":"2606.22082","title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","created":"2026-06-20","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":"2405.16854","title":"Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"agents"},{"id":"2510.17925","title":"SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2602.09447","title":"SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents","created":"2026-02-10","cited_by_count":3,"area":"agents"},{"id":"2604.26963","title":"MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems","created":"2026-04-14","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":"2607.00041","title":"ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2503.19271","title":"MARS: Memory-Enhanced Agents with Reflective Self-improvement","created":"2025-03-25","cited_by_count":2,"area":"agents"},{"id":"2603.02631","title":"Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models","created":"2026-03-03","cited_by_count":2,"area":"agents"},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","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":"2607.24882","title":"Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents","created":"2026-07-27","cited_by_count":2,"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":"2512.18080","title":"From Prompt to Product: A Human-Centered Benchmark of Agentic App Generation Systems","created":"2025-12-19","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":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.15690","title":"Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2603.25770","title":"ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation","created":"2026-03-26","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":"2605.23574","title":"Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2606.08151","title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","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":"2603.00601","title":"Theory of Code Space: Do Code Agents Understand Software Architecture?","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2604.03362","title":"ABTest: Behavior-Driven Testing for AI Coding Agents","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2604.04226","title":"SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web","created":"2026-04-05","cited_by_count":0,"area":"agents"},{"id":"2605.29054","title":"Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence","created":"2026-05-27","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":"2606.05574","title":"SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2608.29834","title":"You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.23570","title":"VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.35357","title":"Do Coding Agents Reuse Existing Code or Reinvent the Wheel?","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38269","title":"Zero2Repo: Can Coding Agents Build Repositories from Scratch?","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.11447","title":"Closed-loop evaluation of LLM agents for embedded software development","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}