{"list":"other","total":69,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"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":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2310.03302","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","created":"2023-10-05","cited_by_count":366},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243},{"id":"2402.18679","title":"Data Interpreter: An LLM Agent For Data Science","created":"2024-02-28","cited_by_count":225},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2406.01014","title":"Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration","created":"2024-06-03","cited_by_count":189},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178},{"id":"2404.06474","title":"Autonomous Evaluation and Refinement of Digital Agents","created":"2024-04-09","cited_by_count":137},{"id":"2403.17927","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","created":"2024-03-26","cited_by_count":134},{"id":"2410.02712","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","created":"2024-10-03","cited_by_count":134},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2402.17453","title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning","created":"2024-02-27","cited_by_count":125},{"id":"2409.07703","title":"DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?","created":"2024-09-12","cited_by_count":125},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102},{"id":"2402.11453","title":"MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization","created":"2024-02-18","cited_by_count":102},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87},{"id":"2311.17541","title":"TaskWeaver: A Code-First Agent Framework","created":"2023-11-29","cited_by_count":86},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72},{"id":"2406.16218","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","created":"2024-06-23","cited_by_count":69},{"id":"2408.14033","title":"MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents","created":"2024-08-26","cited_by_count":67},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65},{"id":"2402.04559","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","created":"2024-02-07","cited_by_count":64},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52},{"id":"2406.11638","title":"MASAI: Modular Architecture for Software-engineering AI Agents","created":"2024-06-17","cited_by_count":49},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48},{"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":"1902.07198","title":"Learning to Generalize from Sparse and Underspecified Rewards","created":"2019-02-19","cited_by_count":39},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26},{"id":"2403.08299","title":"AutoDev: Automated AI-Driven Development","created":"2024-03-13","cited_by_count":24}],"next_cursor":null}