{"total":77,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302,"area":"lr"},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2510.04871","title":"Less is More: Recursive Reasoning with Tiny Networks","created":"2025-10-06","cited_by_count":45,"area":"lr"},{"id":"2511.04570","title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","created":"2025-11-06","cited_by_count":42,"area":"lr"},{"id":"2603.08655","title":"OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning","created":"2026-03-09","cited_by_count":39,"area":"lr"},{"id":"2509.26626","title":"Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models","created":"2025-09-30","cited_by_count":35,"area":"lr"},{"id":"2602.10885","title":"Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics","created":"2026-02-11","cited_by_count":26,"area":"lr"},{"id":"2507.13966","title":"Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need","created":"2025-07-18","cited_by_count":13,"area":"lr"},{"id":"2606.19327","title":"Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation","created":"2026-06-17","cited_by_count":13,"area":"lr"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2512.14693","title":"Universal Reasoning Model","created":"2025-12-16","cited_by_count":11,"area":"lr"},{"id":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2510.02125","title":"Do AI Models Perform Human-like Abstract Reasoning Across Modalities?","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2607.20064","title":"PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning","created":"2026-07-22","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":"2508.20068","title":"11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis","created":"2025-08-27","cited_by_count":9,"area":"lr"},{"id":"2512.11847","title":"Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute","created":"2025-12-04","cited_by_count":9,"area":"lr"},{"id":"2507.16863","title":"Position: Reasoning After Perception Means Reasoning Without Vision","created":"2025-07-21","cited_by_count":8,"area":"lr"},{"id":"2508.09848","title":"PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts","created":"2025-08-13","cited_by_count":7,"area":"lr"},{"id":"2510.12563","title":"HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2602.01541","title":"Toward Cognitive Supersensing in Multimodal Large Language Model","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"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":"2506.05523","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2509.18083","title":"Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning","created":"2025-09-22","cited_by_count":5,"area":"lr"},{"id":"2512.21329","title":"Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2602.23681","title":"ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2510.11919","title":"LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2603.02193","title":"Symbol-Equivariant Recurrent Reasoning Models","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2512.21194","title":"VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs","created":"2025-12-24","cited_by_count":3,"area":"lr"},{"id":"2602.18600","title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2603.12133","title":"TopoBench: Benchmarking LLMs on Hard Topological Reasoning","created":"2026-03-12","cited_by_count":3,"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":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2511.20814","title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2601.13705","title":"Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles","created":"2026-01-20","cited_by_count":2,"area":"lr"},{"id":"2602.04248","title":"Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2602.12196","title":"Visual Reasoning Benchmark: Evaluating Multimodal LLMs on Classroom-Authentic Visual Problems from Primary Education","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.02208","title":"Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.20133","title":"Reasoning Gets Harder for LLMs Inside A Dialogue","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2603.25253","title":"MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2608.09217","title":"Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"id":"2510.27544","title":"TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation","created":"2025-10-31","cited_by_count":1,"area":"lr"},{"id":"2512.05760","title":"Evolutionary System 2 Reasoning: An Empirical Proof","created":"2025-12-05","cited_by_count":1,"area":"lr"},{"id":"2512.20812","title":"Semantic Deception: When Reasoning Models Can't Compute an Addition","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2601.16823","title":"Disentangling generalization and memorization in large language models using chess","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2601.21894","title":"Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.13218","title":"Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning","created":"2026-01-23","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":"2606.01462","title":"An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models","created":"2026-05-31","cited_by_count":1,"area":"lr"},{"id":"2610.02200","title":"VISTA: A Visual Harness for Reasoning in an Interactive World","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2505.16048","title":"SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution","created":"2025-05-21","cited_by_count":0,"area":"lr"},{"id":"2602.17831","title":"The Token Games: Evaluating Language Model Reasoning with Puzzle Duels","created":"2026-02-19","cited_by_count":0,"area":"lr"},{"id":"2603.18953","title":"Context Bootstrapped Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2604.16054","title":"Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.08498","title":"MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.12524","title":"Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2605.31031","title":"GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning","created":"2026-05-29","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":"2606.26530","title":"DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2607.02491","title":"G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.06764","title":"Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2608.04670","title":"Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.09888","title":"BDH-CQ: In-Context Learning with Recurrent Latent Reasoning","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.18011","title":"The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic Reasoning","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2609.05988","title":"DART: Distributional Adversarial Recurrent Training for Algorithm Learning","created":"2026-09-05","cited_by_count":0,"area":"lr"},{"id":"2609.19006","title":"WordPolo: Evaluating Language Models Through Iterative Semantic Feedback","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2609.19883","title":"PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.32913","title":"Allspark: Weak to Strong Transfer via Alternating Chain of Thought","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.39967","title":"What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.07646","title":"Matching Object or Relation? Tracing Abstract Reasoning Inside VLMs","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.08680","title":"A Systematic Study of Small Language Models on Abstract Reasoning Tasks","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.18025","title":"SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}