{"list":"other","total":51,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2602.08234","title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning","created":"2026-02-09","cited_by_count":278},{"id":"2411.04468","title":"Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks","created":"2024-11-07","cited_by_count":232},{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223},{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94},{"id":"2502.11133","title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","created":"2025-02-16","cited_by_count":88},{"id":"2407.12821","title":"AutoFlow: Automated Workflow Generation for Large Language Model Agents","created":"2024-07-01","cited_by_count":83},{"id":"2603.03329","title":"AutoHarness: improving LLM agents by automatically synthesizing a code harness","created":"2026-02-10","cited_by_count":76},{"id":"2603.02176","title":"Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale","created":"2026-03-02","cited_by_count":72},{"id":"2601.21557","title":"Meta Context Engineering via Agentic Skill Evolution","created":"2026-01-29","cited_by_count":49},{"id":"2602.01869","title":"Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents","created":"2026-02-02","cited_by_count":47},{"id":"2406.10248","title":"On the Worst Prompt Performance of Large Language Models","created":"2024-06-08","cited_by_count":38},{"id":"2510.26768","title":"AMO-Bench: Large Language Models Still Struggle in High School Math Competitions","created":"2025-10-30","cited_by_count":38},{"id":"2601.04748","title":"When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail","created":"2026-01-08","cited_by_count":35},{"id":"2601.14652","title":"MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks","created":"2026-01-21","cited_by_count":32},{"id":"2603.00718","title":"SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?","created":"2026-02-28","cited_by_count":30},{"id":"2506.17784","title":"AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction","created":"2025-06-21","cited_by_count":25},{"id":"2508.05592","title":"MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy","created":"2025-08-07","cited_by_count":24},{"id":"2601.11100","title":"ReCreate: Reasoning and Creating Domain Agents Driven by Experience","created":"2026-01-16","cited_by_count":24},{"id":"2409.19272","title":"Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios","created":"2024-09-28","cited_by_count":23},{"id":"2505.12215","title":"GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment","created":"2025-05-18","cited_by_count":21},{"id":"2601.07779","title":"OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent","created":"2026-01-12","cited_by_count":21},{"id":"2409.12447","title":"Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts","created":"2024-09-19","cited_by_count":19},{"id":"2411.02093","title":"Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?","created":"2024-11-04","cited_by_count":19},{"id":"2502.14345","title":"FlowAgent: Achieving Compliance and Flexibility for Workflow Agents","created":"2025-02-20","cited_by_count":19},{"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},{"id":"2505.22967","title":"MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming","created":"2025-05-29","cited_by_count":16},{"id":"2601.10343","title":"OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding","created":"2026-01-15","cited_by_count":15},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11},{"id":"2602.01840","title":"Read As Human: Compressing Context via Parallelizable Close Reading and Skimming","created":"2026-02-02","cited_by_count":10},{"id":"2406.13161","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","created":"2024-06-19","cited_by_count":8},{"id":"2601.18285","title":"U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents","created":"2026-01-26","cited_by_count":8},{"id":"2602.07072","title":"AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation","created":"2026-02-05","cited_by_count":8},{"id":"2503.02400","title":"Promptware Engineering: Software Engineering for Prompt-Enabled Systems","created":"2025-03-04","cited_by_count":6},{"id":"2603.00822","title":"ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files","created":"2026-02-28","cited_by_count":6},{"id":"2511.19635","title":"Agint: Agentic Graph Compilation for Software Engineering Agents","created":"2025-11-24","cited_by_count":4},{"id":"2603.07751","title":"3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models","created":"2026-03-08","cited_by_count":4},{"id":"2512.14805","title":"Sharing State Between Prompts and Programs","created":"2025-12-16","cited_by_count":2}],"next_cursor":null}