{"total":127,"rows":[{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2410.12761","title":"SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation","created":"2024-10-16","cited_by_count":133,"area":"diffusion"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2404.02183","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","created":"2024-04-02","cited_by_count":84,"area":"agents"},{"id":"2504.07986","title":"SEAL: Steerable Reasoning Calibration of Large Language Models for Free","created":"2025-04-07","cited_by_count":68,"area":"lr"},{"id":"2507.18224","title":"Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation","created":"2025-07-24","cited_by_count":58,"area":"agents"},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2505.07473","title":"Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks","created":"2025-05-12","cited_by_count":40,"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":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2505.07176","title":"Internet of Agents: Fundamentals, Applications, and Challenges","created":"2025-05-12","cited_by_count":31,"area":"agents"},{"id":"2504.04785","title":"Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors","created":"2025-04-07","cited_by_count":22,"area":"agents"},{"id":"2409.05001","title":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement","created":"2024-09-08","cited_by_count":21,"area":null},{"id":"2411.07464","title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","created":"2024-11-12","cited_by_count":19,"area":"agents"},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2601.00376","title":"In Line with Context: Repository-Level Code Generation via Context Inlining","created":"2026-01-01","cited_by_count":18,"area":null},{"id":"2605.07358","title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","created":"2026-05-08","cited_by_count":18,"area":"agents"},{"id":"2510.07475","title":"MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference","created":"2025-10-08","cited_by_count":17,"area":"agents"},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2505.13516","title":"HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems","created":"2025-05-17","cited_by_count":13,"area":"agents"},{"id":"2506.14234","title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","created":"2025-06-17","cited_by_count":13,"area":"lr"},{"id":"2504.19099","title":"VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction","created":"2025-04-27","cited_by_count":12,"area":null},{"id":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11,"area":"lr"},{"id":"2502.18489","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2505.23953","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2506.10948","title":"Execution Guided Line-by-Line Code Generation","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2510.09854","title":"NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering","created":"2025-10-10","cited_by_count":10,"area":null},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"area":"alignment"},{"id":"2411.02317","title":"Defining and Evaluating Physical Safety for Large Language Models","created":"2024-11-04","cited_by_count":9,"area":null},{"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":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2502.02928","title":"Large Language Model Guided Self-Debugging Code Generation","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"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":"2408.11326","title":"Automating Thought of Search: A Journey Towards Soundness and Completeness","created":"2024-08-21","cited_by_count":7,"area":"lr"},{"id":"2501.18784","title":"Successor-Generator Planning with LLM-generated Heuristics","created":"2025-01-30","cited_by_count":7,"area":null},{"id":"2606.09071","title":"REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces","created":"2026-06-08","cited_by_count":7,"area":"agents"},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2406.05381","title":"Experimenting with Multi-Agent Software Development: Towards a Unified Platform","created":"2024-06-08","cited_by_count":6,"area":"agents"},{"id":"2412.05187","title":"SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot","created":"2024-12-06","cited_by_count":6,"area":"agents"},{"id":"2508.02053","title":"ProCut: LLM Prompt Compression via Attribution Estimation","created":"2025-08-04","cited_by_count":6,"area":"inference"},{"id":"2509.02330","title":"ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation","created":"2025-09-02","cited_by_count":6,"area":"rag"},{"id":"2408.11198","title":"Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2502.19091","title":"Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation","created":"2025-02-26","cited_by_count":5,"area":"lr"},{"id":"2506.11003","title":"EmbedAgent: Benchmarking Large Language Models in Embedded System Development","created":"2025-04-19","cited_by_count":5,"area":null},{"id":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2507.21485","title":"HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5,"area":null},{"id":"2512.07993","title":"SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2603.15707","title":"SEMAG: Self-Evolutionary Multi-Agent Code Generation","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2504.20412","title":"kAgent: An execution-guided crash resolution agent for the Linux kernel","created":"2025-04-29","cited_by_count":4,"area":"agents"},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.17548","title":"CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning","created":"2025-07-23","cited_by_count":4,"area":"lr"},{"id":"2510.04787","title":"Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2405.13057","title":"Can Github issues be solved with Tree Of Thoughts?","created":"2024-05-20","cited_by_count":3,"area":"lr"},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2502.17442","title":"Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement","created":"2024-12-30","cited_by_count":3,"area":"lr"},{"id":"2506.13824","title":"MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2512.24635","title":"DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2601.20379","title":"Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2603.20260","title":"ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2607.08010","title":"Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems","created":"2026-07-09","cited_by_count":3,"area":"agents"},{"id":"2607.19338","title":"CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents","created":"2026-07-21","cited_by_count":3,"area":"agents"},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2410.15966","title":"Self-Explained Keywords Empower Large Language Models for Code Generation","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2501.02725","title":"Advances in Artificial Intelligence: A Review for the Creative Industries","created":"2025-01-06","cited_by_count":2,"area":"diffusion"},{"id":"2502.12669","title":"Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.15080","title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2505.17482","title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2505.20737","title":"RRO: LLM Agent Optimization Through Rising Reward Trajectories","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"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":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2511.07998","title":"Self-Correction Distillation for Structured Data Question Answering","created":"2025-11-11","cited_by_count":2,"area":null},{"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":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.07248","title":"PaT: Planning-after-Trial for Efficient Test-Time Code Generation","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2605.11922","title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2606.16496","title":"REFLEX: Reflective Evolution from LLM Experience","created":"2026-06-15","cited_by_count":2,"area":"mllm"},{"id":"2410.09780","title":"Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning","created":"2024-10-13","cited_by_count":1,"area":"lr"},{"id":"2501.12106","title":"Can open source large language models be used for tumor documentation in Germany? -- An evaluation on urological doctors' notes","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.14547","title":"(P)rior(D)yna(F)low: A Priori Dynamic Workflow Construction via Multi-Agent Collaboration","created":"2025-09-18","cited_by_count":1,"area":"agents"},{"id":"2510.04089","title":"SPOGW: a Score-based Preference Optimization method via Group-Wise comparison for workflows","created":"2025-10-05","cited_by_count":1,"area":"agents"},{"id":"2602.05905","title":"Codified Finite-state Machines for Role-playing","created":"2026-02-05","cited_by_count":1,"area":null}],"next_cursor":"100"}