{"total":89,"rows":[{"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":"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,"area":"wm"},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2404.04326","title":"Hypothesis Generation with Large Language Models","created":"2024-04-05","cited_by_count":71,"area":null},{"id":"2403.13315","title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","created":"2024-03-20","cited_by_count":57,"area":"lr"},{"id":"2406.17055","title":"Large Language Models Assume People are More Rational than We Really are","created":"2024-06-24","cited_by_count":54,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"id":"2407.07086","title":"Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models","created":"2024-07-09","cited_by_count":48,"area":"agents"},{"id":"2401.06961","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","created":"2024-01-13","cited_by_count":44,"area":"lr"},{"id":"2502.09858","title":"Automated Hypothesis Validation with Agentic Sequential Falsifications","created":"2025-02-14","cited_by_count":44,"area":"agents"},{"id":"2402.17879","title":"Automated Statistical Model Discovery with Language Models","created":"2024-02-27","cited_by_count":41,"area":null},{"id":"2504.11524","title":"HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation","created":"2025-04-15","cited_by_count":37,"area":null},{"id":"2402.13610","title":"Data-driven Discovery with Large Generative Models","created":"2024-02-21","cited_by_count":34,"area":null},{"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":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"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":"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":"2312.13382","title":"DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines","created":"2023-12-20","cited_by_count":27,"area":null},{"id":"2406.08316","title":"Is Programming by Example solved by LLMs?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26,"area":"wm"},{"id":"2501.03916","title":"Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback","created":"2025-01-07","cited_by_count":25,"area":"lr"},{"id":"2402.06025","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","created":"2024-02-08","cited_by_count":24,"area":"lr"},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2509.04439","title":"ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory","created":"2025-09-04","cited_by_count":24,"area":"lr"},{"id":"2411.02429","title":"IdeaBench: Benchmarking Large Language Models for Research Idea Generation","created":"2024-10-31","cited_by_count":23,"area":null},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21,"area":null},{"id":"2410.17309","title":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","created":"2024-10-22","cited_by_count":20,"area":null},{"id":"2501.01540","title":"BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery","created":"2025-01-02","cited_by_count":18,"area":null},{"id":"2404.04286","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","created":"2024-04-04","cited_by_count":17,"area":null},{"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":"2501.14304","title":"MASTER: A Multi-Agent System with LLM Specialized MCTS","created":"2025-01-24","cited_by_count":16,"area":"agents"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2403.15737","title":"Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning","created":"2024-03-23","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":"2503.00902","title":"Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction","created":"2025-03-02","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":"2410.24105","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","created":"2024-10-31","cited_by_count":9,"area":"synth"},{"id":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"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":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2410.24005","title":"Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models","created":"2024-10-31","cited_by_count":8,"area":null},{"id":"2411.00186","title":"Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments","created":"2024-10-31","cited_by_count":8,"area":null},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","cited_by_count":8,"area":"lr"},{"id":"2410.06392","title":"Counterfactual Causal Inference in Natural Language with Large Language Models","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2502.13170","title":"Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment","created":"2025-02-17","cited_by_count":6,"area":"lr"},{"id":"2505.17873","title":"MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2511.15703","title":"Think Visually, Reason Textually: Vision-Language Synergy in ARC","created":"2025-11-19","cited_by_count":6,"area":null},{"id":"2505.18071","title":"Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2601.22623","title":"SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"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":"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":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2401.02985","title":"Evaluating Large Language Models on the GMAT: Implications for the Future of Business Education","created":"2024-01-02","cited_by_count":3,"area":null},{"id":"2412.08985","title":"KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?","created":"2024-12-12","cited_by_count":3,"area":"rag"},{"id":"2502.17541","title":"Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2505.21396","title":"Augmenting Research Ideation with Data: An Empirical Investigation in Social Science","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2601.04963","title":"Text as a Universal Interface for Transferable Personalization","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2602.07983","title":"Accelerating Social Science Research via Agentic Hypothesization and Experimentation","created":"2026-02-08","cited_by_count":3,"area":"agents"},{"id":"2504.09387","title":"On Language Models' Sensitivity to Suspicious Coincidences","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.21486","title":"Hypothesis Generation via LLM-Automated Language Bias for ILP","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2602.07943","title":"IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery","created":"2026-02-08","cited_by_count":2,"area":"agents"},{"id":"2605.10141","title":"FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models","created":"2026-05-11","cited_by_count":2,"area":"alignment"},{"id":"2407.12830","title":"Knowledge-based Consistency Testing of Large Language Models","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2502.15147","title":"Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2505.14744","title":"Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2507.08870","title":"GUIDE: Towards Scalable Advising for Research Ideas","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.01763","title":"Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2510.05962","title":"MatheMagic: Generating Dynamic Mathematics Benchmarks Robust to Memorization","created":"2025-10-07","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":"2606.02556","title":"HERO'S JOURNEY: Testing Complex Rule Induction with Text Games","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2312.00170","title":"When Is Inductive Inference Possible?","created":"2023-11-30","cited_by_count":0,"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":"2502.02315","title":"Shuttle Between the Instructions and the Parameters of Large Language Models","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2505.17481","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2510.19698","title":"RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.06289","title":"How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?","created":"2026-01-09","cited_by_count":0,"area":"lr"},{"id":"2605.24528","title":"Hypothesis Generation and Inductive Inference in Children and Language Models","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.13020","title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.22961","title":"Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.03461","title":"Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.13879","title":"Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired Representations","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.39140","title":"Schema: Discovering Unknown Environments via Agentic Program Induction","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}