{"total":78,"rows":[{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383,"area":"agents"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195,"area":null},{"id":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"area":"synth"},{"id":"2404.18400","title":"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models","created":"2024-04-29","cited_by_count":133,"area":null},{"id":"2401.12954","title":"Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding","created":"2024-01-23","cited_by_count":117,"area":null},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106,"area":null},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2406.04271","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","created":"2024-06-06","cited_by_count":91,"area":"lr"},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89,"area":"lr"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2502.00212","title":"STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving","created":"2025-01-31","cited_by_count":79,"area":"lr"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61,"area":"synth"},{"id":"2310.19791","title":"LILO: Learning Interpretable Libraries by Compressing and Documenting Code","created":"2023-10-30","cited_by_count":49,"area":null},{"id":"2402.11291","title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","created":"2024-02-17","cited_by_count":45,"area":"lr"},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"id":"2407.00695","title":"Learning Formal Mathematics From Intrinsic Motivation","created":"2024-06-30","cited_by_count":45,"area":null},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43,"area":null},{"id":"2502.16789","title":"AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay","created":"2025-02-24","cited_by_count":42,"area":null},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2503.14434","title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","created":"2025-03-18","cited_by_count":38,"area":null},{"id":"2402.03755","title":"QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model","created":"2024-02-06","cited_by_count":30,"area":"synth"},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2402.04858","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","created":"2024-02-07","cited_by_count":23,"area":"lr"},{"id":"2306.14101","title":"Language models are weak learners","created":"2023-06-25","cited_by_count":22,"area":null},{"id":"2212.09246","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","created":"2022-12-19","cited_by_count":21,"area":"distill"},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2309.04316","title":"Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2402.04627","title":"SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2502.04295","title":"Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","cited_by_count":13,"area":"synth"},{"id":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"area":"synth"},{"id":"2305.13917","title":"Generating Data for Symbolic Language with Large Language Models","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2404.04627","title":"Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement","created":"2024-04-06","cited_by_count":12,"area":"lr"},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2406.06887","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","created":"2024-06-11","cited_by_count":8,"area":"alignment"},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2410.19290","title":"Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning","created":"2024-10-25","cited_by_count":7,"area":"synth"},{"id":"2310.10692","title":"ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2410.03303","title":"SELU: Self-Learning Embodied MLLMs in Unknown Environments","created":"2024-10-04","cited_by_count":6,"area":"mllm"},{"id":"2505.14116","title":"Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2402.02456","title":"tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2310.09690","title":"Configuration Validation with Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2406.17873","title":"Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback","created":"2024-06-25","cited_by_count":4,"area":"lr"},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2410.05406","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","cited_by_count":3,"area":"synth"},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2505.07768","title":"Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2310.18076","title":"Knowledge Corpus Error in Question Answering","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2501.01834","title":"MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning","created":"2025-01-03","cited_by_count":2,"area":"agents"},{"id":"2502.12492","title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2510.00373","title":"Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.25223","title":"FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data","created":"2025-10-29","cited_by_count":2,"area":"agents"},{"id":"2311.07635","title":"Past as a Guide: Leveraging Retrospective Learning for Python Code Completion","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2405.20183","title":"A Survey Study on the State of the Art of Programming Exercise Generation using Large Language Models","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2503.08131","title":"Large Scale Multi-Task Bayesian Optimization with Large Language Models","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2509.03537","title":"AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models","created":"2025-08-27","cited_by_count":1,"area":"lr"},{"id":"2603.12597","title":"Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs","created":"2026-03-13","cited_by_count":1,"area":"agents"},{"id":"2603.27836","title":"Q-Bridge: Code Translation for Quantum Machine Learning via LLMs","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2507.15889","title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing","created":"2025-07-20","cited_by_count":0,"area":"synth"},{"id":"2607.02390","title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.34205","title":"Learning to Optimize through Solver-Grounded Self-Play","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2610.15708","title":"SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.15888","title":"Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}