{"total":68,"rows":[{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51,"area":"lr"},{"id":"2604.24594","title":"Skill Retrieval Augmentation for Agentic AI","created":"2026-04-27","cited_by_count":44,"area":"agents"},{"id":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2506.04810","title":"Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2502.12470","title":"Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"area":"lr"},{"id":"2506.10963","title":"MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning","created":"2025-06-12","cited_by_count":16,"area":"lr"},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2508.08344","title":"What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2406.06590","title":"Are LLMs classical or nonmonotonic reasoners? Lessons from generics","created":"2024-06-05","cited_by_count":7,"area":"lr"},{"id":"2505.11854","title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","created":"2025-05-17","cited_by_count":7,"area":"lr"},{"id":"2506.00309","title":"Evaluation of LLMs for mathematical problem solving","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2509.05489","title":"Self-Aligned Reward: Towards Effective and Efficient Reasoners","created":"2025-09-05","cited_by_count":7,"area":"lr"},{"id":"2509.25851","title":"MuSLR: Multimodal Symbolic Logical Reasoning","created":"2025-09-30","cited_by_count":7,"area":"lr"},{"id":"2504.20213","title":"Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2505.17654","title":"EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection","created":"2025-05-23","cited_by_count":5,"area":"mllm"},{"id":"2508.13214","title":"Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","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":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2509.18458","title":"CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2512.22334","title":"SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence","created":"2025-12-26","cited_by_count":3,"area":null},{"id":"2601.12444","title":"Large Language Model for OWL Proofs","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2504.12312","title":"Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles","created":"2025-04-09","cited_by_count":2,"area":"lr"},{"id":"2504.16056","title":"Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability","created":"2025-04-22","cited_by_count":2,"area":"distill"},{"id":"2505.00001","title":"Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning","created":"2025-03-25","cited_by_count":2,"area":"lr"},{"id":"2509.22480","title":"Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2608.22753","title":"Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models","created":"2026-08-24","cited_by_count":2,"area":"lr"},{"id":"2609.26863","title":"SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2504.07080","title":"DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning","created":"2025-04-09","cited_by_count":1,"area":"lr"},{"id":"2504.20771","title":"Computational Reasoning of Large Language Models","created":"2025-04-29","cited_by_count":1,"area":"lr"},{"id":"2505.04736","title":"The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2508.13718","title":"Generics and Default Reasoning in Large Language Models","created":"2025-08-19","cited_by_count":1,"area":"lr"},{"id":"2510.09340","title":"Deductive Logic in Language Models: Horizontal vs Vertical Reasoning","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2512.10758","title":"Designing AI-Resilient Assessments Using Interconnected Problems: A Theoretically Grounded and Empirically Validated Framework","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2602.12665","title":"Evaluating Robustness of Reasoning Models on Parameterized Logical Problems","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2602.21044","title":"LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.18614","title":"ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMs","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2603.20673","title":"PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs","created":"2026-03-21","cited_by_count":1,"area":"rag"},{"id":"2604.02733","title":"DeltaLogic: Minimal Premise Edits Reveal Belief-Revision Failures in Logical Reasoning Models","created":"2026-04-03","cited_by_count":1,"area":"lr"},{"id":"2604.04177","title":"Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2605.06444","title":"SCRuB: Social Concept Reasoning under Rubric-Based Evaluation","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2607.14528","title":"Controlled Reformulation Testing for Logical Consistency in Large Language Models","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2609.02438","title":"When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models","created":"2026-09-02","cited_by_count":1,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2509.08862","title":"Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2512.10561","title":"Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2601.00095","title":"Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.19160","title":"Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing","created":"2026-02-22","cited_by_count":0,"area":"lr"},{"id":"2603.23867","title":"Can VLMs Reason Robustly? A Neuro-Symbolic Investigation","created":"2026-03-25","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":"2604.20523","title":"Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.24305","title":"ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2605.28306","title":"Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models","created":"2026-05-27","cited_by_count":0,"area":"moe"},{"id":"2608.26832","title":"RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.18779","title":"CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.28442","title":"Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.36722","title":"ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2609.38409","title":"ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01605","title":"Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.05489","title":"SkillGATE: Gate-Aware Monte Carlo Tree Search for Skill Retrieval","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}