{"list":"other","total":53,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","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":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292},{"id":"2402.01145","title":"ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution","created":"2024-02-02","cited_by_count":276},{"id":"2401.02051","title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","created":"2024-01-04","cited_by_count":268},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"2303.08233","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","created":"2023-03-14","cited_by_count":135},{"id":"2402.10172","title":"OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models","created":"2024-02-15","cited_by_count":109},{"id":"2501.08603","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","created":"2025-01-15","cited_by_count":109},{"id":"2410.13213","title":"LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch","created":"2024-10-17","cited_by_count":102},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80},{"id":"2312.14890","title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes","created":"2023-12-22","cited_by_count":79},{"id":"2412.14995","title":"HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs","created":"2024-12-19","cited_by_count":73},{"id":"2504.20879","title":"The Leaderboard Illusion","created":"2025-04-29","cited_by_count":66},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52},{"id":"2112.08541","title":"BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing","created":"2021-12-16","cited_by_count":50},{"id":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49},{"id":"2410.08288","title":"Towards Foundation Models for Mixed Integer Linear Programming","created":"2024-10-10","cited_by_count":31},{"id":"2101.01332","title":"Equality Saturation for Tensor Graph Superoptimization","created":"2021-01-05","cited_by_count":27},{"id":"2405.17950","title":"Self-Guiding Exploration for Combinatorial Problems","created":"2024-05-28","cited_by_count":22},{"id":"1609.09353","title":"Deep Multi-Species Embedding","created":"2016-09-28","cited_by_count":20},{"id":"1906.08809","title":"A Deep Reinforcement Learning Approach for Global Routing","created":"2019-06-20","cited_by_count":20},{"id":"2404.04815","title":"Allo: A Programming Model for Composable Accelerator Design","created":"2024-04-07","cited_by_count":16},{"id":"2302.08005","title":"Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training","created":"2023-02-16","cited_by_count":11},{"id":"2108.09523","title":"Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning","created":"2021-08-21","cited_by_count":9},{"id":"2406.06593","title":"Differentiable Combinatorial Scheduling at Scale","created":"2024-06-06","cited_by_count":6},{"id":"2010.00134","title":"Machine Learning in Airline Crew Pairing to Construct Initial Clusters for Dynamic Constraint Aggregation","created":"2020-09-30","cited_by_count":4},{"id":"2003.03792","title":"Real-World Airline Crew Pairing Optimization: Customized Genetic Algorithm versus Column Generation Method","created":"2020-03-08","cited_by_count":1}],"next_cursor":null}