{"total":80,"rows":[{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2503.01773","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","created":"2025-03-03","cited_by_count":95,"area":"lr"},{"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":"2311.08734","title":"Thread of Thought Unraveling Chaotic Contexts","created":"2023-11-15","cited_by_count":72,"area":"lr"},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2406.02061","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","created":"2024-06-04","cited_by_count":68,"area":"lr"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"id":"2312.17080","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","created":"2023-12-28","cited_by_count":57,"area":"lr"},{"id":"2407.08733","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","created":"2024-07-11","cited_by_count":48,"area":"lr"},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2604.07822","title":"Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers","created":"2026-04-09","cited_by_count":37,"area":"lr"},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2406.04229","title":"The CLRS-Text Algorithmic Reasoning Language Benchmark","created":"2024-06-06","cited_by_count":28,"area":"lr"},{"id":"2505.18761","title":"How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark","created":"2025-05-24","cited_by_count":28,"area":"lr"},{"id":"2405.04669","title":"Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics","created":"2024-05-07","cited_by_count":27,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2601.22311","title":"Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents","created":"2026-01-29","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":"2401.09395","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","created":"2024-01-17","cited_by_count":20,"area":"lr"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"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":"2508.10736","title":"Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs","created":"2025-08-14","cited_by_count":13,"area":"lr"},{"id":"2402.03941","title":"Discovering and Reasoning of Causality in the Hidden World with Large Language Models","created":"2024-02-06","cited_by_count":10,"area":"lr"},{"id":"2408.09529","title":"Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path","created":"2024-08-18","cited_by_count":10,"area":"lr"},{"id":"2506.10887","title":"Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers","created":"2025-06-12","cited_by_count":10,"area":"lr"},{"id":"2507.10624","title":"Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning","created":"2025-07-14","cited_by_count":9,"area":"lr"},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2505.20630","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2407.21531","title":"Can LLMs \"Reason\" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation","created":"2024-07-31","cited_by_count":7,"area":"lr"},{"id":"2406.07393","title":"Large Language Models are Limited in Out-of-Context Knowledge Reasoning","created":"2024-06-11","cited_by_count":6,"area":"lr"},{"id":"2312.03633","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","created":"2023-12-06","cited_by_count":5,"area":"lr"},{"id":"2601.08258","title":"Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment","created":"2026-01-13","cited_by_count":5,"area":"lr"},{"id":"2602.21226","title":"IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2505.20021","title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2607.00341","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2310.03309","title":"Concise and Organized Perception Facilitates Reasoning in Large Language Models","created":"2023-10-05","cited_by_count":3,"area":"lr"},{"id":"2502.17800","title":"Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training","created":"2025-02-25","cited_by_count":3,"area":"lr"},{"id":"2503.16401","title":"Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them","created":"2025-03-20","cited_by_count":3,"area":"lr"},{"id":"2506.17296","title":"Semantic uncertainty in advanced decoding methods for LLM generation","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2601.01095","title":"NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding","created":"2026-01-03","cited_by_count":3,"area":"lr"},{"id":"2602.02366","title":"ReasonCACHE: Teaching LLMs To Reason Without Weight Updates","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2501.01246","title":"Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion","created":"2025-01-02","cited_by_count":2,"area":"lr"},{"id":"2503.10408","title":"Out-of-Context Reasoning in Large Language Models","created":"2025-03-13","cited_by_count":2,"area":"lr"},{"id":"2509.16866","title":"seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs","created":"2025-09-21","cited_by_count":2,"area":"lr"},{"id":"2601.12269","title":"Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language Models","created":"2026-01-18","cited_by_count":2,"area":"lr"},{"id":"2602.02470","title":"Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.05120","title":"Certifiable Boolean Reasoning Is Universal","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2603.28038","title":"Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2507.11954","title":"The benefits of query-based KGQA systems for complex and temporal questions in LLM era","created":"2025-07-16","cited_by_count":1,"area":"lr"},{"id":"2601.22035","title":"Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2605.02442","title":"Measuring AI Reasoning: A Guide for Researchers","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2607.00447","title":"Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2502.19907","title":"Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation","created":"2025-02-27","cited_by_count":0,"area":"lr"},{"id":"2507.04189","title":"SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding","created":"2025-07-05","cited_by_count":0,"area":"lr"},{"id":"2601.10810","title":"Digital Metabolism: Decoupling Logic from Facts via Regenerative Unlearning -- Towards a Pure Neural Logic Core","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2602.06446","title":"CORE: Comprehensive Ontological Relation Evaluation for Large Language Models","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2602.15868","title":"Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2603.27694","title":"Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2604.03557","title":"When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression","created":"2026-04-04","cited_by_count":0,"area":"lr"},{"id":"2604.13065","title":"Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM Logic","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2605.09678","title":"Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.12918","title":"CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.12578","title":"MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.12731","title":"Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.27103","title":"The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2606.30653","title":"The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2608.21919","title":"Beyond Fixed Directions: Adaptive Representation Analysis of Reasoning and Memorization in LLMs","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.13948","title":"Thought without systematicity? Evaluating reasoning models on rule induction tasks","created":"2026-09-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}