{"total":82,"rows":[{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197,"area":null},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120,"area":"lr"},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"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":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2311.09247","title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","created":"2023-11-14","cited_by_count":55,"area":"lr"},{"id":"2402.01207","title":"Efficient Causal Graph Discovery Using Large Language Models","created":"2024-02-02","cited_by_count":53,"area":null},{"id":"2502.09858","title":"Automated Hypothesis Validation with Agentic Sequential Falsifications","created":"2025-02-14","cited_by_count":44,"area":"agents"},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2403.11793","title":"Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus","created":"2024-03-18","cited_by_count":32,"area":"lr"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30,"area":"mllm"},{"id":"2504.05081","title":"The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning","created":"2025-04-07","cited_by_count":30,"area":"lr"},{"id":"2408.00114","title":"Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs","created":"2024-07-31","cited_by_count":29,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"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":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2410.21287","title":"A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education","created":"2024-10-11","cited_by_count":16,"area":"lr"},{"id":"2403.02513","title":"Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF","created":"2024-03-04","cited_by_count":15,"area":"alignment"},{"id":"2405.15880","title":"HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2502.11176","title":"LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning","created":"2025-02-16","cited_by_count":12,"area":"lr"},{"id":"2310.05146","title":"Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge","created":"2023-10-08","cited_by_count":11,"area":"lr"},{"id":"2310.08773","title":"Examining the Potential and Pitfalls of ChatGPT in Science and Engineering Problem-Solving","created":"2023-10-12","cited_by_count":11,"area":null},{"id":"2403.01390","title":"Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering","created":"2024-03-03","cited_by_count":11,"area":"lr"},{"id":"2410.08126","title":"Mars: Situated Inductive Reasoning in an Open-World Environment","created":"2024-10-10","cited_by_count":11,"area":"lr"},{"id":"2502.08946","title":"The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2410.06405","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","created":"2024-10-08","cited_by_count":10,"area":"lr"},{"id":"2504.05089","title":"Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2505.08778","title":"ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus","created":"2025-05-13","cited_by_count":10,"area":"lr"},{"id":"2506.15746","title":"Neural Cellular Automata for ARC-AGI","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2407.18069","title":"$\\text{C}^2\\text{P}$: Featuring Large Language Models with Causal Reasoning","created":"2024-07-25","cited_by_count":8,"area":"lr"},{"id":"2410.02651","title":"CAX: Cellular Automata Accelerated in JAX","created":"2024-10-03","cited_by_count":8,"area":null},{"id":"2412.07322","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","created":"2024-12-10","cited_by_count":8,"area":"lr"},{"id":"2505.01177","title":"LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures","created":"2025-05-02","cited_by_count":8,"area":null},{"id":"2602.20532","title":"Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training","created":"2026-02-24","cited_by_count":8,"area":null},{"id":"2403.09734","title":"Do Large Language Models Solve ARC Visual Analogies Like People Do?","created":"2024-03-13","cited_by_count":7,"area":"lr"},{"id":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2408.12212","title":"Relational decomposition for program synthesis","created":"2024-08-22","cited_by_count":6,"area":null},{"id":"2506.02648","title":"Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation","created":"2025-06-03","cited_by_count":6,"area":"lr"},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2401.11725","title":"Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models","created":"2024-01-22","cited_by_count":4,"area":null},{"id":"2401.16215","title":"Learning big logical rules by joining small rules","created":"2024-01-29","cited_by_count":4,"area":null},{"id":"2405.06399","title":"Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus","created":"2024-05-10","cited_by_count":4,"area":"lr"},{"id":"2502.07190","title":"Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2505.24225","title":"Reasoning Can Hurt the Inductive Abilities of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":"lr"},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2509.21874","title":"Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"id":"2511.21714","title":"GPS: General Per-Sample Prompter","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2605.22613","title":"Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2409.11041","title":"Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2410.11756","title":"Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2411.17438","title":"Object-centric proto-symbolic behavioural reasoning from pixels","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2411.18158","title":"Abductive Symbolic Solver on Abstraction and Reasoning Corpus","created":"2024-11-27","cited_by_count":2,"area":"lr"},{"id":"2501.04424","title":"NSA: Neuro-symbolic ARC Challenge","created":"2025-01-08","cited_by_count":2,"area":"lr"},{"id":"2505.17482","title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2505.20672","title":"GIFARC: Synthetic Dataset for Leveraging Human-Intuitive Analogies to Elevate AI Reasoning","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2508.20818","title":"cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending","created":"2025-08-28","cited_by_count":2,"area":"agents"},{"id":"2510.08804","title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2512.11013","title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2606.12316","title":"Slots, Transitions, Loops: Learning Composable World Models for ARC","created":"2026-06-10","cited_by_count":2,"area":"wm"},{"id":"2401.02072","title":"ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers","created":"2024-01-04","cited_by_count":1,"area":null},{"id":"2407.18968","title":"Intelligence Analysis of Language Models","created":"2024-07-20","cited_by_count":1,"area":"lr"},{"id":"2508.06230","title":"Learning Logical Rules using Minimum Message Length","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2511.08747","title":"Vector Symbolic Algebras for the Abstraction and Reasoning Corpus","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.12390","title":"Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2607.29586","title":"TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2410.07866","title":"System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2503.07554","title":"An Empirical Comparison of Cost Functions in Inductive Logic Programming","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2506.06739","title":"Honey, I shrunk the hypothesis space (through logical preprocessing)","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2509.01016","title":"Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2604.12018","title":"LLMs Struggle with Abstract Meaning Comprehension More Than Expected","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.23106","title":"No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2605.31031","title":"GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2607.11758","title":"From Global to Factor-Wise Expert Composition in Discrete Diffusion Models","created":"2026-07-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.19006","title":"WordPolo: Evaluating Language Models Through Iterative Semantic Feedback","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2610.00820","title":"On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.13660","title":"Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}