{"total":112,"rows":[{"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":"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":"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":"2410.17809","title":"An Intelligent Agentic System for Complex Image Restoration Problems","created":"2024-10-23","cited_by_count":43,"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":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2512.23738","title":"Enforcing Temporal Constraints for LLM Agents","created":"2025-12-25","cited_by_count":34,"area":"agents"},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","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":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2506.19290","title":"Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs","created":"2025-06-24","cited_by_count":26,"area":"agents"},{"id":"2410.22932","title":"Multi-Agent Large Language Models for Conversational Task-Solving","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2505.13941","title":"MLZero: A Multi-Agent System for End-to-end Machine Learning Automation","created":"2025-05-20","cited_by_count":24,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2503.06664","title":"Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets","created":"2025-03-09","cited_by_count":20,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2506.13977","title":"CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios","created":"2025-06-11","cited_by_count":19,"area":"agents"},{"id":"2601.20404","title":"On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents","created":"2026-01-28","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":"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":"2603.04474","title":"From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration","created":"2026-03-04","cited_by_count":14,"area":"agents"},{"id":"2510.21903","title":"TOM-SWE: User Mental Modeling For Software Engineering Agents","created":"2025-10-24","cited_by_count":13,"area":"agents"},{"id":"2511.02755","title":"Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2511.21398","title":"Prune4Web: DOM Tree Pruning Programming for Web Agent","created":"2025-11-26","cited_by_count":12,"area":"agents"},{"id":"2504.14557","title":"Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction","created":"2025-04-20","cited_by_count":11,"area":"agents"},{"id":"2505.20128","title":"Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers","created":"2025-05-26","cited_by_count":11,"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":"2412.17146","title":"LLM Agent for Fire Dynamics Simulations","created":"2024-12-22","cited_by_count":10,"area":"agents"},{"id":"2510.04017","title":"Zephyrus: An Agentic Framework for Weather Science","created":"2025-10-05","cited_by_count":10,"area":"agents"},{"id":"2508.11425","title":"Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments","created":"2025-08-15","cited_by_count":9,"area":"agents"},{"id":"2510.05414","title":"A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis","created":"2025-10-06","cited_by_count":9,"area":"agents"},{"id":"2602.23647","title":"SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair","created":"2026-02-27","cited_by_count":9,"area":"agents"},{"id":"2502.20859","title":"The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents","created":"2025-02-28","cited_by_count":8,"area":"agents"},{"id":"2503.07044","title":"DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation","created":"2025-03-10","cited_by_count":8,"area":"agents"},{"id":"2504.07634","title":"Agent That Debugs: Dynamic State-Guided Vulnerability Repair","created":"2025-04-10","cited_by_count":7,"area":"agents"},{"id":"2507.23096","title":"ChatVis: Large Language Model Agent for Generating Scientific Visualizations","created":"2025-07-30","cited_by_count":7,"area":"agents"},{"id":"2602.03045","title":"Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2605.07769","title":"Coding Agents Don't Know When to Act","created":"2026-05-08","cited_by_count":7,"area":"agents"},{"id":"2504.12961","title":"QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?","created":"2025-04-17","cited_by_count":6,"area":"agents"},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","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":"2409.06336","title":"Towards Agentic AI on Particle Accelerators","created":"2024-09-10","cited_by_count":5,"area":"agents"},{"id":"2505.03906","title":"MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing","created":"2025-05-06","cited_by_count":5,"area":"agents"},{"id":"2511.09804","title":"SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations","created":"2025-11-12","cited_by_count":5,"area":"agents"},{"id":"2503.12217","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","created":"2025-03-15","cited_by_count":4,"area":"agents"},{"id":"2503.20036","title":"Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft","created":"2025-03-25","cited_by_count":4,"area":"agents"},{"id":"2505.04628","title":"How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks","created":"2025-04-04","cited_by_count":4,"area":"agents"},{"id":"2508.18675","title":"Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision","created":"2025-08-26","cited_by_count":4,"area":"agents"},{"id":"2510.10460","title":"Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2601.19583","title":"Toward Architecture-Aware Evaluation Metrics for LLM Agents","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2602.01405","title":"Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents","created":"2026-02-01","cited_by_count":4,"area":"agents"},{"id":"2603.25226","title":"WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing","created":"2026-03-26","cited_by_count":4,"area":"agents"},{"id":"2604.06861","title":"REAgent: Requirement-Driven LLM Agents for Software Issue Resolution","created":"2026-04-08","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":"2506.19481","title":"LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code","created":"2025-06-24","cited_by_count":3,"area":"agents"},{"id":"2510.17603","title":"ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2601.19747","title":"Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2605.08426","title":"Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2605.17475","title":"Event-B Agent: Towards LLM Agent for Formal Model Synthesis and Repair","created":"2026-05-17","cited_by_count":3,"area":"agents"},{"id":"2606.08610","title":"HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning","created":"2026-06-07","cited_by_count":3,"area":"agents"},{"id":"2506.20598","title":"Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges","created":"2025-06-25","cited_by_count":2,"area":"agents"},{"id":"2507.09481","title":"Evaluating LLMs on Sequential API Call Through Automated Test Generation","created":"2025-07-13","cited_by_count":2,"area":"agents"},{"id":"2508.01858","title":"Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents","created":"2025-08-03","cited_by_count":2,"area":"agents"},{"id":"2509.19918","title":"Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation","created":"2025-09-24","cited_by_count":2,"area":"agents"},{"id":"2510.16381","title":"ATA: A Neuro-Symbolic Approach to Implement Autonomous and Trustworthy Agents","created":"2025-10-18","cited_by_count":2,"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":"2512.02329","title":"Towards autonomous normative multi-agent systems for Human-AI software engineering teams","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2512.21818","title":"Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development","created":"2025-12-26","cited_by_count":2,"area":"agents"},{"id":"2512.23742","title":"AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization","created":"2025-12-26","cited_by_count":2,"area":"agents"},{"id":"2602.02597","title":"ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2410.18529","title":"Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents","created":"2024-10-24","cited_by_count":1,"area":"agents"},{"id":"2510.18483","title":"StarBench: A Turn-Based RPG Benchmark for Agentic Multimodal Decision-Making and Information Seeking","created":"2025-10-21","cited_by_count":1,"area":"agents"},{"id":"2512.11589","title":"A Study of Library Usage in Agent-Authored Pull Requests","created":"2025-12-12","cited_by_count":1,"area":"agents"},{"id":"2601.21115","title":"Multi-task Code LLMs: Data Mix or Model Merge?","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2602.02138","title":"CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems","created":"2026-02-02","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":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2605.20351","title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.24138","title":"Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2608.05223","title":"Towards a Risk Assessment of Malicious Skill Files in Coding Agents","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2502.07928","title":"Distributed Approach to Haskell Based Applications Refactoring with LLMs Based Multi-Agent Systems","created":"2025-02-11","cited_by_count":0,"area":"agents"},{"id":"2505.04354","title":"Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows","created":"2025-05-07","cited_by_count":0,"area":"agents"},{"id":"2508.11665","title":"StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution","created":"2025-08-06","cited_by_count":0,"area":"agents"},{"id":"2509.03310","title":"app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding","created":"2025-09-03","cited_by_count":0,"area":"agents"},{"id":"2510.19274","title":"From Specification to Service: Accelerating API-First Development Using Multi-Agent Systems","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2510.19868","title":"Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2510.21902","title":"Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2511.02071","title":"Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing","created":"2025-11-03","cited_by_count":0,"area":"agents"},{"id":"2511.03934","title":"PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2512.01089","title":"CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents","created":"2025-11-30","cited_by_count":0,"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":"2602.06975","title":"BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents","created":"2026-01-16","cited_by_count":0,"area":"agents"},{"id":"2603.21178","title":"LLM-based Automated Architecture View Generation: Where Are We Now?","created":"2026-03-22","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":"2604.10300","title":"From Helpful to Trustworthy: LLM Agents for Pair Programming","created":"2026-04-11","cited_by_count":0,"area":"agents"},{"id":"2605.15237","title":"A3D: Agentic AI flow for autonomous Accelerator Design","created":"2026-05-14","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}