{"list":"other","total":55,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"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":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"2309.17288","title":"AutoAgents: A Framework for Automatic Agent Generation","created":"2023-09-29","cited_by_count":216},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193},{"id":"2502.04180","title":"Multi-agent Architecture Search via Agentic Supernet","created":"2025-02-06","cited_by_count":179},{"id":"2410.02506","title":"Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems","created":"2024-10-03","cited_by_count":141},{"id":"2305.16504","title":"On the Tool Manipulation Capability of Open-source Large Language Models","created":"2023-05-25","cited_by_count":122},{"id":"2410.11782","title":"G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks","created":"2024-10-15","cited_by_count":119},{"id":"2502.02533","title":"Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies","created":"2025-02-04","cited_by_count":113},{"id":"2508.20453","title":"MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers","created":"2025-08-28","cited_by_count":109},{"id":"2508.14704","title":"MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers","created":"2025-08-20","cited_by_count":96},{"id":"2312.14033","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","created":"2023-12-21","cited_by_count":93},{"id":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63},{"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},{"id":"2412.17481","title":"A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application","created":"2024-12-23","cited_by_count":55},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48},{"id":"2505.16700","title":"MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models","created":"2025-05-22","cited_by_count":48},{"id":"2508.01780","title":"LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?","created":"2025-08-03","cited_by_count":48},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46},{"id":"2410.08115","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","created":"2024-10-10","cited_by_count":43},{"id":"2406.14884","title":"FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents","created":"2024-06-21","cited_by_count":40},{"id":"2506.07672","title":"MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents","created":"2025-06-09","cited_by_count":38},{"id":"2507.12806","title":"MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models","created":"2025-07-17","cited_by_count":36},{"id":"2602.03786","title":"AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration","created":"2026-02-03","cited_by_count":35},{"id":"2506.02951","title":"Adaptive Graph Pruning for Multi-Agent Communication","created":"2025-06-03","cited_by_count":29},{"id":"2506.08119","title":"SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents","created":"2025-06-09","cited_by_count":23},{"id":"2602.19672","title":"SkillOrchestra: Learning to Route Agents via Skill Transfer","created":"2026-02-23","cited_by_count":23},{"id":"2506.09790","title":"ComfyUI-R1: Exploring Reasoning Models for Workflow Generation","created":"2025-06-11","cited_by_count":15},{"id":"2601.12560","title":"Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents","created":"2026-01-18","cited_by_count":14},{"id":"2602.17100","title":"AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation","created":"2026-02-19","cited_by_count":13},{"id":"2510.07799","title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","created":"2025-10-09","cited_by_count":11},{"id":"2507.11988","title":"Aime: Towards Fully-Autonomous Multi-Agent Framework","created":"2025-07-16","cited_by_count":9},{"id":"2509.04642","title":"Maestro: Joint Graph & Config Optimization for Reliable AI Agents","created":"2025-09-04","cited_by_count":9},{"id":"2601.19290","title":"MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning","created":"2026-01-27","cited_by_count":9},{"id":"2504.16005","title":"CAPO: Cost-Aware Prompt Optimization","created":"2025-04-22","cited_by_count":7},{"id":"2602.06511","title":"EvoMAS: Evolutionary Generation of Multi-Agent Systems","created":"2026-02-06","cited_by_count":5}],"next_cursor":null}