{"total":114,"rows":[{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737,"area":"agents"},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198,"area":"agents"},{"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":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2506.07398","title":"G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems","created":"2025-06-09","cited_by_count":122,"area":"agents"},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120,"area":"agents"},{"id":"2409.03215","title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","created":"2024-09-05","cited_by_count":111,"area":"agents"},{"id":"2402.11453","title":"MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization","created":"2024-02-18","cited_by_count":102,"area":"agents"},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90,"area":"agents"},{"id":"2502.11133","title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","created":"2025-02-16","cited_by_count":88,"area":"agents"},{"id":"2408.08927","title":"VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool","created":"2024-08-15","cited_by_count":85,"area":"agents"},{"id":"2408.09667","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","created":"2024-08-19","cited_by_count":77,"area":"agents"},{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76,"area":"agents"},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57,"area":"agents"},{"id":"2410.04587","title":"Hammer: Robust Function-Calling for On-Device Language Models via Function Masking","created":"2024-10-06","cited_by_count":55,"area":"agents"},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2501.18160","title":"RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing","created":"2025-01-30","cited_by_count":49,"area":"agents"},{"id":"2409.03797","title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls","created":"2024-09-04","cited_by_count":48,"area":"agents"},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"id":"2407.01231","title":"MIRAI: Evaluating LLM Agents for Event Forecasting","created":"2024-07-01","cited_by_count":41,"area":"agents"},{"id":"2404.17153","title":"UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging","created":"2024-04-26","cited_by_count":35,"area":"agents"},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34,"area":"agents"},{"id":"2502.05664","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","created":"2025-02-08","cited_by_count":32,"area":"agents"},{"id":"2410.14209","title":"Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents","created":"2024-10-18","cited_by_count":26,"area":"agents"},{"id":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"id":"2407.16732","title":"PyBench: Evaluating LLM Agent on various real-world coding tasks","created":"2024-07-23","cited_by_count":24,"area":"agents"},{"id":"2402.01411","title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","created":"2024-02-02","cited_by_count":22,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2404.12753","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation","created":"2024-04-19","cited_by_count":20,"area":"agents"},{"id":"2502.00988","title":"PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback","created":"2025-02-03","cited_by_count":20,"area":"agents"},{"id":"2504.20115","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","created":"2025-04-28","cited_by_count":20,"area":"agents"},{"id":"2512.14895","title":"Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections","created":"2025-12-16","cited_by_count":19,"area":"agents"},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2406.06469","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","created":"2024-06-10","cited_by_count":16,"area":"agents"},{"id":"2509.13941","title":"An Empirical Study on Failures in Automated Issue Solving","created":"2025-09-17","cited_by_count":16,"area":"agents"},{"id":"2502.06111","title":"CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories","created":"2025-02-10","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":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2408.05006","title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","created":"2024-08-09","cited_by_count":13,"area":"agents"},{"id":"2412.10422","title":"AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework","created":"2024-12-10","cited_by_count":12,"area":"agents"},{"id":"2503.18455","title":"SEAlign: Alignment Training for Software Engineering Agent","created":"2025-03-24","cited_by_count":11,"area":"agents"},{"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":"2511.08522","title":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models","created":"2025-11-11","cited_by_count":11,"area":"agents"},{"id":"2408.06849","title":"Causal Agent based on Large Language Model","created":"2024-08-13","cited_by_count":10,"area":"agents"},{"id":"2502.00406","title":"Agents Are All You Need for LLM Unlearning","created":"2025-02-01","cited_by_count":10,"area":"agents"},{"id":"2512.01311","title":"CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL","created":"2025-12-01","cited_by_count":10,"area":"agents"},{"id":"2504.04220","title":"AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation","created":"2025-04-05","cited_by_count":8,"area":"agents"},{"id":"2605.16045","title":"RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents","created":"2026-05-15","cited_by_count":8,"area":"agents"},{"id":"2504.19277","title":"Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling","created":"2025-04-27","cited_by_count":7,"area":"agents"},{"id":"2510.18779","title":"KAT-Coder Technical Report","created":"2025-10-21","cited_by_count":7,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6,"area":"agents"},{"id":"2510.23642","title":"VisCoder2: Building Multi-Language Visualization Coding Agents","created":"2025-10-24","cited_by_count":6,"area":"agents"},{"id":"2507.15640","title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","created":"2025-07-21","cited_by_count":5,"area":"agents"},{"id":"2602.19547","title":"CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents","created":"2026-02-23","cited_by_count":5,"area":"agents"},{"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":"2503.12217","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","created":"2025-03-15","cited_by_count":4,"area":"agents"},{"id":"2507.13814","title":"CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education","created":"2025-07-18","cited_by_count":4,"area":"agents"},{"id":"2511.00517","title":"Issue-Oriented Agent-Based Framework for Automated Review Comment Generation","created":"2025-11-01","cited_by_count":4,"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":"2604.06861","title":"REAgent: Requirement-Driven LLM Agents for Software Issue Resolution","created":"2026-04-08","cited_by_count":4,"area":"agents"},{"id":"2410.06949","title":"Towards Exception Safety Code Generation with Intermediate Representation Agents Framework","created":"2024-10-09","cited_by_count":3,"area":"agents"},{"id":"2503.15129","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","created":"2025-03-19","cited_by_count":3,"area":"agents"},{"id":"2509.17489","title":"MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM","created":"2025-09-22","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":"2606.11290","title":"FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse","created":"2026-06-09","cited_by_count":3,"area":"agents"},{"id":"2412.11713","title":"Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework","created":"2024-12-16","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":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2502.18515","title":"Securing Smart Contract Languages with a Unified Agentic Framework for Vulnerability Repair in Solidity and Move","created":"2025-02-22","cited_by_count":1,"area":"agents"},{"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":"2508.00632","title":"Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings","created":"2025-08-01","cited_by_count":1,"area":"agents"},{"id":"2510.03323","title":"Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision","created":"2025-10-01","cited_by_count":1,"area":"agents"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2601.18113","title":"MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs","created":"2026-01-26","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":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2607.03316","title":"Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild","created":"2026-07-03","cited_by_count":1,"area":"agents"},{"id":"2607.17205","title":"A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code Agents","created":"2026-07-19","cited_by_count":1,"area":"agents"},{"id":"2607.18886","title":"TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development","created":"2026-07-21","cited_by_count":1,"area":"agents"},{"id":"2607.24604","title":"Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2412.08069","title":"DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production","created":"2024-12-11","cited_by_count":0,"area":"agents"},{"id":"2505.23946","title":"Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve","created":"2025-05-29","cited_by_count":0,"area":"agents"},{"id":"2507.15892","title":"StaAgent: An Agentic Framework for Testing Static Analyzers","created":"2025-07-20","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":"2510.11076","title":"DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education","created":"2025-10-13","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":"2511.03934","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":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2512.20957","title":"One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents","created":"2025-12-24","cited_by_count":0,"area":"agents"},{"id":"2604.10800","title":"Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis","created":"2026-04-12","cited_by_count":0,"area":"agents"},{"id":"2604.23557","title":"DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2605.17444","title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","created":"2026-05-17","cited_by_count":0,"area":"agents"},{"id":"2606.05250","title":"Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language Model","created":"2026-06-03","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}