{"list":"other","total":55,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"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":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2401.06591","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","created":"2024-01-12","cited_by_count":125},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111},{"id":"2501.03936","title":"PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides","created":"2025-01-07","cited_by_count":86},{"id":"2508.13167","title":"Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL","created":"2025-08-06","cited_by_count":80},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66},{"id":"2505.21497","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","created":"2025-05-27","cited_by_count":63},{"id":"2404.09992","title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","created":"2024-04-15","cited_by_count":55},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54},{"id":"2502.14191","title":"Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models","created":"2025-02-20","cited_by_count":44},{"id":"2509.06216","title":"Agentic Software Engineering: Foundational Pillars and a Research Roadmap","created":"2025-09-07","cited_by_count":41},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39},{"id":"2311.01767","title":"PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion","created":"2023-11-03","cited_by_count":30},{"id":"2503.11069","title":"API Agents vs. GUI Agents: Divergence and Convergence","created":"2025-03-14","cited_by_count":29},{"id":"2510.18212","title":"A Definition of AGI","created":"2025-10-21","cited_by_count":27},{"id":"2509.11062","title":"Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations","created":"2025-09-14","cited_by_count":19},{"id":"2508.10146","title":"Agentic AI Frameworks: Architectures, Protocols, and Design Challenges","created":"2025-08-13","cited_by_count":16},{"id":"2503.05977","title":"Is Your Video Language Model a Reliable Judge?","created":"2025-03-07","cited_by_count":14},{"id":"2510.02418","title":"BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks","created":"2025-10-02","cited_by_count":14},{"id":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11},{"id":"2403.03788","title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","created":"2024-03-06","cited_by_count":9},{"id":"2507.16403","title":"ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering","created":"2025-07-22","cited_by_count":8},{"id":"2509.25154","title":"Who's Your Judge? On the Detectability of LLM-Generated Judgments","created":"2025-09-29","cited_by_count":8},{"id":"2510.12750","title":"VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage","created":"2025-10-14","cited_by_count":7},{"id":"2505.19662","title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","created":"2025-05-26","cited_by_count":6},{"id":"2509.16811","title":"Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media","created":"2025-09-20","cited_by_count":6},{"id":"2505.21755","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","created":"2025-05-27","cited_by_count":5},{"id":"2508.03630","title":"SlideAudit: A Dataset and Taxonomy for Automated Evaluation of Presentation Slides","created":"2025-08-05","cited_by_count":3},{"id":"2507.03916","title":"Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language Models","created":"2025-07-05","cited_by_count":1},{"id":"2508.07021","title":"DocRefine: An Intelligent Framework for Scientific Document Understanding and Content Optimization based on Multimodal Large Model Agents","created":"2025-08-09","cited_by_count":1}],"next_cursor":null}