{"total":38,"rows":[{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129,"area":null},{"id":"2310.13227","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","created":"2023-10-20","cited_by_count":105,"area":null},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51,"area":null},{"id":"2307.10719","title":"LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?","created":"2023-07-20","cited_by_count":49,"area":null},{"id":"2311.10775","title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","created":"2023-11-15","cited_by_count":45,"area":null},{"id":"2403.17918","title":"AgentStudio: A Toolkit for Building General Virtual Agents","created":"2024-03-26","cited_by_count":45,"area":null},{"id":"2401.12491","title":"Assessing and Understanding Creativity in Large Language Models","created":"2024-01-23","cited_by_count":35,"area":null},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2502.10709","title":"An Empirical Analysis of Uncertainty in Large Language Model Evaluations","created":"2025-02-15","cited_by_count":20,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2410.11710","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2402.09615","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2410.10872","title":"ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2511.00457","title":"GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining","created":"2025-11-01","cited_by_count":5,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2311.09635","title":"Evaluating In-Context Learning of Libraries for Code Generation","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2410.08442","title":"JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2507.00487","title":"MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2511.19957","title":"AppSelectBench: Application-Level Tool Selection Benchmark","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2512.00672","title":"ML-Tool-Bench: Tool-Augmented Planning for ML Tasks","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2409.09191","title":"ProcessTBench: An LLM Plan Generation Dataset for Process Mining","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2409.15523","title":"SEAL: Suite for Evaluating API-use of LLMs","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2604.27763","title":"Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.10555","title":"Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2312.00268","title":"Academic competitions","created":"2023-12-01","cited_by_count":0,"area":null}],"next_cursor":null}