{"list":"other","total":58,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273},{"id":"2307.05300","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","created":"2023-07-11","cited_by_count":251},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2402.18679","title":"Data Interpreter: An LLM Agent For Data Science","created":"2024-02-28","cited_by_count":225},{"id":"2502.04180","title":"Multi-agent Architecture Search via Agentic Supernet","created":"2025-02-06","cited_by_count":179},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158},{"id":"2305.14688","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","created":"2023-05-24","cited_by_count":142},{"id":"2402.16906","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","created":"2024-02-25","cited_by_count":127},{"id":"2406.18532","title":"Symbolic Learning Enables Self-Evolving Agents","created":"2024-06-26","cited_by_count":106},{"id":"2401.08500","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","created":"2024-01-16","cited_by_count":103},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72},{"id":"2502.11271","title":"OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning","created":"2025-02-16","cited_by_count":69},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60},{"id":"2503.03686","title":"MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems","created":"2025-03-05","cited_by_count":50},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33},{"id":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32},{"id":"2404.14963","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","created":"2024-04-23","cited_by_count":31},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30},{"id":"2410.04444","title":"G\\\"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement","created":"2024-10-06","cited_by_count":29},{"id":"2402.15505","title":"Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts","created":"2024-02-23","cited_by_count":28},{"id":"2406.11033","title":"HAIChart: Human and AI Paired Visualization System","created":"2024-06-16","cited_by_count":26},{"id":"2404.18144","title":"Generative AI for Visualization: State of the Art and Future Directions","created":"2024-04-28","cited_by_count":23},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20},{"id":"2308.05481","title":"LLM As DBA","created":"2023-08-10","cited_by_count":18},{"id":"2005.14311","title":"SourceFinder: Finding Malware Source-Code from Publicly Available Repositories","created":"2020-05-28","cited_by_count":15},{"id":"2406.19032","title":"Improving Weak-to-Strong Generalization with Reliability-Aware Alignment","created":"2024-06-27","cited_by_count":14},{"id":"2412.00420","title":"TAROT: Targeted Data Selection via Optimal Transport","created":"2024-11-30","cited_by_count":9},{"id":"2312.05621","title":"PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching","created":"2023-12-09","cited_by_count":6}],"next_cursor":null}