{"list":"other","total":62,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"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":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"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":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"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":"1802.08802","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","created":"2018-02-24","cited_by_count":284},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2306.07863","title":"Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control","created":"2023-06-13","cited_by_count":187},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160},{"id":"2403.02713","title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","created":"2024-03-05","cited_by_count":159},{"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":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"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":"2305.16504","title":"On the Tool Manipulation Capability of Open-source Large Language Models","created":"2023-05-25","cited_by_count":122},{"id":"2312.11671","title":"Evaluating Language-Model Agents on Realistic Autonomous Tasks","created":"2023-12-18","cited_by_count":96},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72},{"id":"2306.00245","title":"From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces","created":"2023-05-31","cited_by_count":68},{"id":"2209.08655","title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","created":"2022-09-18","cited_by_count":66},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2402.06596","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","created":"2024-02-09","cited_by_count":60},{"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":"2311.10775","title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","created":"2023-11-15","cited_by_count":45},{"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":"2305.08144","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","created":"2023-05-14","cited_by_count":36},{"id":"2404.16054","title":"LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation","created":"2024-04-12","cited_by_count":36},{"id":"2403.08140","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","created":"2024-03-12","cited_by_count":34},{"id":"2201.08896","title":"Environment Generation for Zero-Shot Compositional Reinforcement Learning","created":"2022-01-21","cited_by_count":32},{"id":"2104.08560","title":"Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments","created":"2021-04-17","cited_by_count":28},{"id":"2310.08740","title":"A Zero-Shot Language Agent for Computer Control with Structured Reflection","created":"2023-10-12","cited_by_count":28},{"id":"2106.00133","title":"AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning","created":"2021-05-31","cited_by_count":17}],"next_cursor":null}