{"total":59,"rows":[{"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":"2601.01885","title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","created":"2026-01-05","cited_by_count":78,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2511.01884","title":"CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization","created":"2025-10-23","cited_by_count":45,"area":"agents"},{"id":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2510.25779","title":"Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets","created":"2025-10-27","cited_by_count":19,"area":"agents"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2512.07921","title":"DeepCode: Open Agentic Coding","created":"2025-12-08","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":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","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":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2603.10085","title":"KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization","created":"2026-03-10","cited_by_count":11,"area":"agents"},{"id":"2512.18733","title":"Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection","created":"2025-12-21","cited_by_count":9,"area":"agents"},{"id":"2509.25297","title":"Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2603.05637","title":"Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy","created":"2026-03-05","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":"2510.03902","title":"Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-Code","created":"2025-10-04","cited_by_count":5,"area":"agents"},{"id":"2510.26852","title":"CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2602.03219","title":"Beyond Quantity: Trajectory Diversity Scaling for Code Agents","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2602.20478","title":"Codified Context: Infrastructure for AI Agents in a Complex Codebase","created":"2026-02-24","cited_by_count":5,"area":"agents"},{"id":"2603.08721","title":"KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware","created":"2026-02-10","cited_by_count":5,"area":"agents"},{"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":"2603.13258","title":"Your Code Agent Can Grow Alongside You with Structured Memory","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2604.25135","title":"FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments","created":"2026-04-28","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":"2512.21250","title":"CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents","created":"2025-12-24","cited_by_count":3,"area":"agents"},{"id":"2601.09503","title":"What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding","created":"2026-01-14","cited_by_count":3,"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":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2511.09794","title":"Evaluating Software Process Models for Multi-Agent Class-Level Code Generation","created":"2025-11-12","cited_by_count":2,"area":"agents"},{"id":"2602.19000","title":"MagicAgent: Towards Generalized Agent Planning","created":"2026-02-22","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":"2604.14609","title":"El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2604.26615","title":"TDD Governance for Multi-Agent Code Generation via Prompt Engineering","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2605.02741","title":"AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2605.20456","title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","created":"2026-05-19","cited_by_count":2,"area":"agents"},{"id":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2608.18933","title":"SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2601.18202","title":"SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback","created":"2026-01-26","cited_by_count":1,"area":"agents"},{"id":"2602.02760","title":"From Task Solving to Robust Real-World Adaptation in LLM Agents","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.21551","title":"AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2604.24697","title":"Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2606.12474","title":"SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems","created":"2026-06-10","cited_by_count":1,"area":"agents"},{"id":"2607.04212","title":"An Evaluation of Role-Based Multi-Agent Code Generation on Repository-Scale Problems","created":"2026-07-05","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2601.05467","title":"STELP: Secure Transpilation and Execution of LLM-Generated Programs","created":"2026-01-09","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":"2604.12421","title":"Agentic Insight Generation in VSM Simulations","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2605.21470","title":"Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2607.00407","title":"Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.26083","title":"Cross-Model Cross-Language AI Coding Agent Performance: Accuracy and Speed of Parallel CLRS Algorithms","created":"2026-07-26","cited_by_count":0,"area":"agents"},{"id":"2607.28825","title":"Building a Process-Modeling Tool using Agentic AI: An Experience Report on PM4Py-UCM","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.13884","title":"Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.24234","title":"The Work Behind Delegation: A Framework for Supervising AI Coding Agents","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.24348","title":"A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach","created":"2026-09-21","cited_by_count":0,"area":"agents"}],"next_cursor":null}