{"total":86,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142,"area":"agents"},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81,"area":"lr"},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2505.19443","title":"Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI","created":"2025-05-26","cited_by_count":42,"area":"agents"},{"id":"2504.19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects","created":"2025-04-28","cited_by_count":32,"area":"agents"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2509.21766","title":"UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios","created":"2025-09-26","cited_by_count":26,"area":"agents"},{"id":"2505.15859","title":"AutoData: A Multi-Agent System for Open Web Data Collection","created":"2025-05-21","cited_by_count":25,"area":"agents"},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2412.03624","title":"How to Correctly do Semantic Backpropagation on Language-based Agentic Systems","created":"2024-12-04","cited_by_count":18,"area":"agents"},{"id":"2508.18298","title":"Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms","created":"2025-08-22","cited_by_count":18,"area":"agents"},{"id":"2509.01835","title":"From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs","created":"2025-09-01","cited_by_count":18,"area":"agents"},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2412.18371","title":"Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents","created":"2024-12-24","cited_by_count":16,"area":"agents"},{"id":"2508.07935","title":"SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows","created":"2025-08-11","cited_by_count":13,"area":"agents"},{"id":"2410.01242","title":"RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance","created":"2024-10-02","cited_by_count":12,"area":"agents"},{"id":"2503.01895","title":"Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"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":"2410.15625","title":"Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces","created":"2024-10-21","cited_by_count":11,"area":null},{"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":"2510.09901","title":"Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics","created":"2025-10-10","cited_by_count":11,"area":"agents"},{"id":"2601.15075","title":"The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution","created":"2026-01-21","cited_by_count":11,"area":"agents"},{"id":"2509.05941","title":"Code2MCP: Transforming Code Repositories into MCP Services","created":"2025-09-07","cited_by_count":10,"area":"agents"},{"id":"2510.07614","title":"Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines","created":"2025-10-08","cited_by_count":10,"area":"agents"},{"id":"2505.02133","title":"Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency","created":"2025-05-04","cited_by_count":9,"area":"agents"},{"id":"2510.09244","title":"Fundamentals of Building Autonomous LLM Agents","created":"2025-10-10","cited_by_count":8,"area":"agents"},{"id":"2512.17912","title":"Graph-O1 : Monte Carlo Tree Search with Reinforcement Learning for Text-Attributed Graph Reasoning","created":"2025-11-26","cited_by_count":7,"area":"lr"},{"id":"2412.08593","title":"Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks","created":"2024-12-11","cited_by_count":6,"area":"rag"},{"id":"2508.01012","title":"AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents","created":"2025-08-01","cited_by_count":6,"area":"agents"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2508.12358","title":"Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2509.25894","title":"Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities","created":"2025-09-30","cited_by_count":5,"area":"agents"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2601.18226","title":"Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks","created":"2026-01-26","cited_by_count":5,"area":null},{"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":"2506.17772","title":"PAGENT: Learning to Patch Software Engineering Agents","created":"2025-06-21","cited_by_count":4,"area":"agents"},{"id":"2508.07745","title":"Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation","created":"2025-08-11","cited_by_count":4,"area":"agents"},{"id":"2508.16678","title":"Cognitive Agents Powered by Large Language Models for Agile Software Project Management","created":"2025-08-21","cited_by_count":4,"area":"agents"},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2601.19583","title":"Toward Architecture-Aware Evaluation Metrics for LLM Agents","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2409.11190","title":"SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer","created":"2024-09-17","cited_by_count":3,"area":"rag"},{"id":"2410.15222","title":"AutoFLUKA: A Large Language Model Based Framework for Automating Monte Carlo Simulations in FLUKA","created":"2024-10-19","cited_by_count":3,"area":null},{"id":"2412.17964","title":"Dynamic Multi-Agent Orchestration and Retrieval for Multi-Source Question-Answer Systems using Large Language Models","created":"2024-12-23","cited_by_count":3,"area":"agents"},{"id":"2601.18827","title":"Automated structural testing of LLM-based agents: methods, framework, and case studies","created":"2026-01-25","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":"2605.06717","title":"Agentic Coding Needs Proactivity, Not Just Autonomy","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2506.18315","title":"Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2510.13982","title":"Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations","created":"2025-10-15","cited_by_count":2,"area":"agents"},{"id":"2606.26614","title":"HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization","created":"2026-06-25","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":"2412.17942","title":"Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents","created":"2024-12-23","cited_by_count":1,"area":"agents"},{"id":"2501.19056","title":"Enabling Autonomic Microservice Management through Self-Learning Agents","created":"2025-01-31","cited_by_count":1,"area":"agents"},{"id":"2507.04043","title":"Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2507.08392","title":"Multi-Agent LLMs as Ethics Advocates for AI-Based Systems","created":"2025-07-11","cited_by_count":1,"area":"agents"},{"id":"2509.02411","title":"A Survey: Towards Privacy and Security in Mobile Large Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.15259","title":"SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2511.15752","title":"Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics","created":"2025-11-19","cited_by_count":1,"area":"agents"},{"id":"2605.02592","title":"Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2605.13280","title":"Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code","created":"2026-05-13","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":"2605.27631","title":"Poison with Style: A Practical Poisoning Attack on Code Large Language Models","created":"2026-05-26","cited_by_count":1,"area":null},{"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":"2411.08294","title":"Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka","created":"2024-11-13","cited_by_count":0,"area":"agents"},{"id":"2502.00229","title":"When and How to Integrate Multimodal Large Language Models in College Psychotherapy: Perspectives from Multi-stakeholders","created":"2025-02-01","cited_by_count":0,"area":"mllm"},{"id":"2506.00002","title":"Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2507.01315","title":"Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agent","created":"2025-07-02","cited_by_count":0,"area":"agents"},{"id":"2507.19904","title":"CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2508.08761","title":"DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation","created":"2025-08-12","cited_by_count":0,"area":"agents"},{"id":"2510.10179","title":"LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.18551","title":"SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2511.04157","title":"Are We Aligned? A Preliminary Investigation of the Alignment of Responsible AI Values between LLMs and Human Judgment","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2602.01222","title":"FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2602.16997","title":"Exploring LLMs for User Story Extraction from Mockups","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.16325","title":"A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.24784","title":"GRAIL: AI translation for scientists application workflow on satellite data","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.05646","title":"Enhancing Software Engineering Through Closed-Loop Memory Optimization","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.09182","title":"Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering","created":"2026-06-08","cited_by_count":0,"area":"agents"},{"id":"2607.28942","title":"NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability","created":"2026-07-31","cited_by_count":0,"area":"lr"},{"id":"2608.14863","title":"Evaluating Agentic Code Repair Capabilities in Distributed Systems","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.00023","title":"ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Design","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.39107","title":"MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.08662","title":"ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}