{"total":145,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105,"area":null},{"id":"2407.20183","title":"MindSearch: Mimicking Human Minds Elicits Deep AI Searcher","created":"2024-07-29","cited_by_count":66,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2603.25723","title":"Natural-Language Agent Harnesses","created":"2026-03-26","cited_by_count":61,"area":null},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2509.24002","title":"MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use","created":"2025-09-28","cited_by_count":39,"area":null},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34,"area":null},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2506.04625","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","created":"2025-06-05","cited_by_count":24,"area":null},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2502.04426","title":"The simulation of judgment in LLMs","created":"2025-02-06","cited_by_count":22,"area":null},{"id":"2405.20092","title":"Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2508.04295","title":"EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation","created":"2025-08-06","cited_by_count":19,"area":null},{"id":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2411.04578","title":"Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2605.10500","title":"SkillEvolver: Skill Learning as a Meta-Skill","created":"2026-05-11","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2509.25651","title":"AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2510.23564","title":"ReCode: Unify Plan and Action for Universal Granularity Control","created":"2025-10-27","cited_by_count":15,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","cited_by_count":12,"area":null},{"id":"2508.02621","title":"HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2409.10756","title":"VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching","created":"2024-09-16","cited_by_count":9,"area":null},{"id":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"area":null},{"id":"2510.16844","title":"FinSight: Towards Real-World Financial Deep Research","created":"2025-10-19","cited_by_count":9,"area":null},{"id":"2510.00510","title":"JoyAgent-JDGenie: Technical Report on the GAIA","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2601.02399","title":"ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2601.03509","title":"Evolving Programmatic Skill Networks","created":"2026-01-07","cited_by_count":7,"area":null},{"id":"2606.16707","title":"User as Code: Executable Memory for Personalized Agents","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2607.21557","title":"OpenForgeRL: Train Harness-native Agents in Any Environment","created":"2026-07-23","cited_by_count":7,"area":null},{"id":"2609.17523","title":"ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents","created":"2026-09-15","cited_by_count":7,"area":null},{"id":"2410.16024","title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2504.07421","title":"AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2602.10525","title":"LHAW: Controllable Underspecification for Long-Horizon Tasks","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2510.23856","title":"From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production","created":"2025-10-27","cited_by_count":5,"area":null},{"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":"2605.22148","title":"Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2506.12202","title":"Quasar: A Programming Language Specialized for LLM Code Actions","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2506.14580","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.05578","title":"Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent","created":"2026-03-05","cited_by_count":4,"area":null},{"id":"2604.19657","title":"An AI Agent Execution Environment to Safeguard User Data","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2605.09730","title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2606.24235","title":"SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2503.14331","title":"ADAPT: An Autonomous Forklift for Construction Site Operation","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2504.11502","title":"Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2509.10210","title":"Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extraction","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2605.17172","title":"OpenJarvis: Personal AI, On Personal Devices","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.08049","title":"SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2607.22798","title":"StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2409.04831","title":"MILE: A Mutation Testing Framework of In-Context Learning Systems","created":"2024-09-07","cited_by_count":2,"area":null},{"id":"2412.11417","title":"RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM Enhancement","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2412.16172","title":"LABIIUM: AI-Enhanced Zero-configuration Measurement Automation System","created":"2024-12-07","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":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.03250","title":"A Versatile Multimodal Agent for Multimedia Content Generation","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2602.00012","title":"OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2602.02711","title":"Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.00058","title":"PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.15653","title":"Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context","created":"2026-03-07","cited_by_count":2,"area":null},{"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":"2605.09366","title":"Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.22505","title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2606.17454","title":"Dissecting model behavior through agent trajectories","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2606.24151","title":"Metis: Bridging Text and Code Memory for Self-Evolving Agents","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2607.02345","title":"SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2410.16392","title":"Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2503.19584","title":"Multi-agent Application System in Office Collaboration Scenarios","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.03991","title":"Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.17539","title":"Proof of Useful Intelligence (PoUI): Blockchain Consensus Beyond Energy Waste","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2507.16203","title":"SVAgent: AI Agent for Hardware Security Verification Assertion","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2508.03487","title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.15411","title":"Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2510.16470","title":"Declarative Techniques for NL Queries over Heterogeneous Data","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2512.25065","title":"Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.04204","title":"TeachMaster: Generative Teaching via Code","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2602.21143","title":"A Benchmark for Deep Information Synthesis","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.20667","title":"REVERE: Reflective Evolving Research Engineer","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2605.01698","title":"BIM Information Extraction Through LLM-based Adaptive Exploration","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.21902","title":"Planning in the LLM Era: Building for Reliability and Efficiency","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.03738","title":"AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null}],"next_cursor":"100"}