{"total":106,"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":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","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":"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":"2510.18165","title":"Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model","created":"2025-10-20","cited_by_count":13,"area":"diffusion"},{"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":"2601.07348","title":"Controlled Self-Evolution for Algorithmic Code Optimization","created":"2026-01-12","cited_by_count":12,"area":null},{"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":"2601.21448","title":"ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2604.07466","title":"Cross-Tokenizer LLM Distillation through a Byte-Level Interface","created":"2026-04-08","cited_by_count":8,"area":null},{"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":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2601.03525","title":"Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation","created":"2026-01-07","cited_by_count":5,"area":"alignment"},{"id":"2601.11650","title":"Large Language Model Agent for User-friendly Chemical Process Simulations","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2602.03219","title":"Beyond Quantity: Trajectory Diversity Scaling for Code Agents","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2602.20217","title":"KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem","created":"2026-02-23","cited_by_count":5,"area":"inference"},{"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":"2509.21054","title":"Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion","created":"2025-09-25","cited_by_count":4,"area":"lr"},{"id":"2511.04014","title":"VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications","created":"2025-11-06","cited_by_count":4,"area":"lr"},{"id":"2512.18567","title":"AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software","created":"2025-12-21","cited_by_count":4,"area":null},{"id":"2601.02752","title":"EComStage: Stage-wise and Orientation-specific Benchmarking for Large Language Models in E-commerce","created":"2026-01-06","cited_by_count":4,"area":null},{"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":"2510.23408","title":"AutoStreamPipe: LLM Assisted Automatic Generation of Data Stream Processing Pipelines","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"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":"2511.18868","title":"KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits","created":"2025-11-24","cited_by_count":2,"area":"inference"},{"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":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"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":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","cited_by_count":2,"area":"synth"},{"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":"2608.09277","title":"P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2608.18933","title":"SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2511.07669","title":"Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2511.20613","title":"Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"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":"2602.17688","title":"AnCoder: Anchored Code Generation via Discrete Diffusion Models","created":"2026-02-05","cited_by_count":1,"area":"diffusion"},{"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":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"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":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2605.19382","title":"PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.27820","title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"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":"2606.16545","title":"Can LLM Coding Agents Reason About Time Series?","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"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":"2607.04537","title":"Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2607.06990","title":"A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.16204","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"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":"2509.23979","title":"ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and Evaluation","created":"2025-09-28","cited_by_count":0,"area":"wm"},{"id":"2511.16787","title":"NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.05467","title":"STELP: Secure Transpilation and Execution of LLM-Generated Programs","created":"2026-01-09","cited_by_count":0,"area":"agents"},{"id":"2603.11687","title":"SemBench: A Universal Semantic Framework for LLM Evaluation","created":"2026-03-12","cited_by_count":0,"area":"lr"},{"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":"2605.05949","title":"MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.13411","title":"Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"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":"2607.16845","title":"From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.16868","title":"Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification","created":"2026-07-18","cited_by_count":0,"area":null},{"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":"2608.03474","title":"MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.05659","title":"Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks","created":"2026-08-06","cited_by_count":0,"area":"safety"},{"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":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.04570","title":"Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}