{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319},{"id":"2310.11441","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","created":"2023-10-17","cited_by_count":299},{"id":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2408.00203","title":"OmniParser for Pure Vision Based GUI Agent","created":"2024-08-01","cited_by_count":198},{"id":"2406.08451","title":"GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices","created":"2024-06-12","cited_by_count":194},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148},{"id":"2008.05756","title":"Metrics for Multi-Class Classification: an Overview","created":"2020-08-13","cited_by_count":143},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137},{"id":"2404.06474","title":"Autonomous Evaluation and Refinement of Digital Agents","created":"2024-04-09","cited_by_count":137},{"id":"2306.06624","title":"RestGPT: Connecting Large Language Models with Real-World RESTful APIs","created":"2023-06-11","cited_by_count":135},{"id":"2404.03648","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","created":"2024-04-04","cited_by_count":130},{"id":"2410.13232","title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","created":"2024-10-17","cited_by_count":126},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2408.15978","title":"WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration","created":"2024-08-28","cited_by_count":101},{"id":"2409.13373","title":"LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench","created":"2024-09-20","cited_by_count":94},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90},{"id":"2407.19056","title":"OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation","created":"2024-07-26","cited_by_count":70},{"id":"2309.08172","title":"LASER: LLM Agent with State-Space Exploration for Web Navigation","created":"2023-09-15","cited_by_count":66},{"id":"2310.03720","title":"SteP: Stacked LLM Policies for Web Actions","created":"2023-10-05","cited_by_count":66},{"id":"2312.06717","title":"Privacy Issues in Large Language Models: A Survey","created":"2023-12-11","cited_by_count":60},{"id":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58},{"id":"2304.07061","title":"DroidBot-GPT: GPT-powered UI Automation for Android","created":"2023-04-14","cited_by_count":47},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45},{"id":"2403.17918","title":"AgentStudio: A Toolkit for Building General Virtual Agents","created":"2024-03-26","cited_by_count":45},{"id":"2406.10819","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","created":"2024-06-16","cited_by_count":43},{"id":"2403.08140","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","created":"2024-03-12","cited_by_count":34},{"id":"2312.11190","title":"VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning","created":"2023-12-18","cited_by_count":28},{"id":"2211.07615","title":"UGIF: UI Grounded Instruction Following","created":"2022-11-14","cited_by_count":25},{"id":"2311.18751","title":"Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web","created":"2023-11-30","cited_by_count":24},{"id":"2404.05902","title":"WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents","created":"2024-04-08","cited_by_count":22},{"id":"2401.04124","title":"MobileAgent: enhancing mobile control via human-machine interaction and SOP integration","created":"2024-01-04","cited_by_count":18},{"id":"2411.10943","title":"Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms","created":"2024-11-17","cited_by_count":13},{"id":"2405.11120","title":"Latent State Estimation Helps UI Agents to Reason","created":"2024-05-17","cited_by_count":9},{"id":"2310.13518","title":"Vision-Based Mobile App GUI Testing: A Survey","created":"2023-10-20","cited_by_count":8},{"id":"2404.08755","title":"Training a Vision Language Model as Smartphone Assistant","created":"2024-04-12","cited_by_count":8},{"id":"2404.10887","title":"Grounded Language Agent for Product Search via Intelligent Web Interactions","created":"2024-04-16","cited_by_count":7},{"id":"2110.08653","title":"Learning UI Navigation through Demonstrations composed of Macro Actions","created":"2021-10-16","cited_by_count":6},{"id":"2405.15341","title":"V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM","created":"2024-05-24","cited_by_count":6},{"id":"2203.07828","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","created":"2022-03-15","cited_by_count":5},{"id":"2406.06947","title":"CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only","created":"2024-06-11","cited_by_count":4},{"id":"2407.01558","title":"Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces","created":"2024-05-05","cited_by_count":3}],"next_cursor":null}