{"total":70,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215,"area":"lr"},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"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":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2409.16191","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","created":"2024-09-24","cited_by_count":44,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2503.20749","title":"Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data","created":"2025-03-26","cited_by_count":28,"area":"agents"},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"area":"lr"},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"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":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2507.21105","title":"AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis","created":"2025-07-08","cited_by_count":13,"area":"agents"},{"id":"2505.10852","title":"MatTools: Benchmarking Large Language Models for Materials Science Tools","created":"2025-05-16","cited_by_count":12,"area":null},{"id":"2503.15520","title":"Agent-S: LLM Agentic workflow to automate Standard Operating Procedures","created":"2025-02-03","cited_by_count":10,"area":"agents"},{"id":"2603.10899","title":"LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation","created":"2026-03-11","cited_by_count":10,"area":"inference"},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2403.13433","title":"AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior","created":"2024-03-20","cited_by_count":6,"area":"wm"},{"id":"2411.03012","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","created":"2024-11-05","cited_by_count":6,"area":null},{"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":"2606.05238","title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","created":"2026-06-03","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":"2411.04156","title":"Crystal: Illuminating LLM Abilities on Language and Code","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2510.19245","title":"See, Think, Act: Online Shopper Behavior Simulation with VLM Agents","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2412.19031","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","created":"2024-12-26","cited_by_count":4,"area":null},{"id":"2412.19770","title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","created":"2024-12-27","cited_by_count":4,"area":"agents"},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2412.08068","title":"Repository-Level Graph Representation Learning for Enhanced Security Patch Detection","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2504.11502","title":"Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2605.24693","title":"CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2405.10243","title":"DocuMint: Docstring Generation for Python using Small Language Models","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2406.04464","title":"On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing","created":"2024-06-06","cited_by_count":2,"area":"lr"},{"id":"2509.08088","title":"EnvX: Agentize Everything with Agentic AI","created":"2025-09-09","cited_by_count":2,"area":"agents"},{"id":"2511.05874","title":"An Empirical Study of Reasoning Steps in Thinking Code LLMs","created":"2025-11-08","cited_by_count":2,"area":"lr"},{"id":"2605.12110","title":"AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference","created":"2026-05-12","cited_by_count":2,"area":"inference"},{"id":"2406.13840","title":"StackRAG Agent: Improving Developer Answers with Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":1,"area":"rag"},{"id":"2503.13279","title":"Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation","created":"2025-03-17","cited_by_count":1,"area":"agents"},{"id":"2511.08060","title":"From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection","created":"2025-11-11","cited_by_count":1,"area":"agents"},{"id":"2512.16956","title":"SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization","created":"2025-12-18","cited_by_count":1,"area":"agents"},{"id":"2604.08426","title":"KV Cache Offloading for Context-Intensive Tasks","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2604.10520","title":"ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2605.14563","title":"Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.17279","title":"Rover: Context-aware Conflict Resolution with LLM","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.18073","title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.18684","title":"Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2504.08852","title":"ML For Hardware Design Interpretability: Challenges and Opportunities","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.00482","title":"Multi-Agent Coordinated Rename Refactoring","created":"2026-01-01","cited_by_count":0,"area":"agents"},{"id":"2605.14634","title":"Documentation-Guided Agentic Codebase Migration from C to Rust","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2606.26490","title":"An Empirical Study of LLM-Generated Specifications for VeriFast","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.30524","title":"The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems","created":"2026-06-29","cited_by_count":0,"area":"rag"},{"id":"2609.06383","title":"From Reading Code to Reading Spec: A Verified Layer for LLM-Driven Codebase Maintenance","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.07586","title":"A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis","created":"2026-09-07","cited_by_count":0,"area":null},{"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":"2610.15708","title":"SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}