{"list":"other","total":58,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"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":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107},{"id":"2401.08500","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","created":"2024-01-16","cited_by_count":103},{"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":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2402.09171","title":"Automated Unit Test Improvement using Large Language Models at Meta","created":"2024-02-14","cited_by_count":75},{"id":"1506.08941","title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning","created":"2015-06-30","cited_by_count":71},{"id":"2404.10100","title":"LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation","created":"2024-04-15","cited_by_count":49},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43},{"id":"2403.18746","title":"CYCLE: Learning to Self-Refine the Code Generation","created":"2024-03-27","cited_by_count":42},{"id":"2405.01466","title":"A Systematic Literature Review on Large Language Models for Automated Program Repair","created":"2024-05-02","cited_by_count":37},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29},{"id":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28},{"id":"2405.16434","title":"The Importance of Directional Feedback for LLM-based Optimizers","created":"2024-05-26","cited_by_count":26},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17},{"id":"2402.07157","title":"Natural Language Reinforcement Learning","created":"2024-02-11","cited_by_count":17},{"id":"2502.01619","title":"Learning to Generate Unit Tests for Automated Debugging","created":"2025-02-03","cited_by_count":17},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16},{"id":"2402.13013","title":"Code Needs Comments: Enhancing Code LLMs with Comment Augmentation","created":"2024-02-20","cited_by_count":16},{"id":"2401.05319","title":"Leveraging Print Debugging to Improve Code Generation in Large Language Models","created":"2024-01-10","cited_by_count":15},{"id":"1908.10449","title":"Interactive Machine Comprehension with Information Seeking Agents","created":"2019-08-27","cited_by_count":13},{"id":"2403.16354","title":"ChatDBG: Augmenting Debugging with Large Language Models","created":"2024-03-25","cited_by_count":9},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9},{"id":"1612.02605","title":"Towards Information-Seeking Agents","created":"2016-12-08","cited_by_count":4},{"id":"2404.07549","title":"Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective","created":"2024-04-11","cited_by_count":3}],"next_cursor":null}