{"total":69,"rows":[{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"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":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"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":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"area":"lr"},{"id":"2402.04379","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","created":"2024-02-06","cited_by_count":93,"area":null},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2405.16247","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","created":"2024-05-25","cited_by_count":61,"area":"agents"},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57,"area":"lr"},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"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":"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":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2402.11442","title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs","created":"2024-02-18","cited_by_count":28,"area":"lr"},{"id":"2410.07484","title":"WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents","created":"2024-10-09","cited_by_count":26,"area":"wm"},{"id":"2503.22165","title":"Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models","created":"2025-03-28","cited_by_count":25,"area":"lr"},{"id":"2408.10455","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","created":"2024-08-19","cited_by_count":22,"area":"agents"},{"id":"2410.04691","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2405.13009","title":"MetaReflection: Learning Instructions for Language Agents using Past Reflections","created":"2024-05-13","cited_by_count":19,"area":"agents"},{"id":"2408.13654","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","created":"2024-08-24","cited_by_count":17,"area":"lr"},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17,"area":null},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2510.18428","title":"AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library","created":"2025-10-21","cited_by_count":14,"area":"synth"},{"id":"2510.22503","title":"LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery","created":"2025-10-26","cited_by_count":13,"area":null},{"id":"2403.06420","title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2405.07474","title":"Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions","created":"2024-05-13","cited_by_count":12,"area":null},{"id":"2407.17695","title":"Enhancing Agent Learning through World Dynamics Modeling","created":"2024-07-25","cited_by_count":9,"area":"agents"},{"id":"2506.23678","title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","created":"2025-06-30","cited_by_count":9,"area":"lr"},{"id":"2403.05789","title":"ItD: Large Language Models Can Teach Themselves Induction through Deduction","created":"2024-03-09","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2409.19019","title":"RAGProbe: An Automated Approach for Evaluating RAG Applications","created":"2024-09-24","cited_by_count":7,"area":"rag"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2401.13849","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","created":"2024-01-24","cited_by_count":6,"area":"lr"},{"id":"2404.11095","title":"Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues","created":"2024-04-17","cited_by_count":6,"area":"alignment"},{"id":"2504.02670","title":"Affordable AI Assistants with Knowledge Graph of Thoughts","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2401.05190","title":"DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs","created":"2024-01-10","cited_by_count":5,"area":"lr"},{"id":"2411.03349","title":"RuAG: Learned-rule-augmented Generation for Large Language Models","created":"2024-11-04","cited_by_count":5,"area":"lr"},{"id":"2504.15785","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","created":"2025-04-22","cited_by_count":5,"area":"wm"},{"id":"2505.21935","title":"From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2408.07840","title":"ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2502.12185","title":"Large Language Models for Extrapolative Modeling of Manufacturing Processes","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2403.00800","title":"Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes","created":"2024-02-23","cited_by_count":3,"area":"lr"},{"id":"2409.10011","title":"HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making","created":"2024-09-16","cited_by_count":3,"area":"rag"},{"id":"2503.11336","title":"Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2503.23487","title":"Large Language and Reasoning Models are Shallow Disjunctive Reasoners","created":"2025-03-30","cited_by_count":3,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2408.12775","title":"Intelligent OPC Engineer Assistant for Semiconductor Manufacturing","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2412.17819","title":"Inductive Linguistic Reasoning with Large Language Models","created":"2024-12-09","cited_by_count":2,"area":"lr"},{"id":"2505.21486","title":"Hypothesis Generation via LLM-Automated Language Bias for ILP","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2510.23532","title":"When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2601.15153","title":"How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework","created":"2026-01-21","cited_by_count":2,"area":"agents"},{"id":"2402.05307","title":"Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2403.17819","title":"Accelerating Radio Spectrum Regulation Workflows with Large Language Models (LLMs)","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2408.05773","title":"Neurosymbolic Methods for Rule Mining","created":"2024-08-11","cited_by_count":1,"area":null},{"id":"2408.09365","title":"Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2410.09428","title":"Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets","created":"2024-10-12","cited_by_count":1,"area":"distill"},{"id":"2410.13018","title":"Learning Representations for Reasoning: Generalizing Across Diverse Structures","created":"2024-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.13935","title":"Big Reasoning with Small Models: Instruction Retrieval at Inference Time","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"id":"2602.11052","title":"GraphSeek: Next-Generation Graph Analytics with LLMs","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2412.13645","title":"On the Role of Model Prior in Real-World Inductive Reasoning","created":"2024-12-18","cited_by_count":0,"area":"lr"},{"id":"2503.01672","title":"Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.00831","title":"SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2604.24972","title":"Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.20924","title":"Strategy-Induct: Task-Level Strategy Induction for Instruction Generation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2609.03213","title":"LLMs Learn Better In-Context from Rules than from Examples","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.04339","title":"ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.12813","title":"VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}