{"total":150,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330,"area":"lr"},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374,"area":"lr"},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"area":"lr"},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2412.04454","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","created":"2024-12-05","cited_by_count":278,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2503.00307","title":"Remasking Discrete Diffusion Models with Inference-Time Scaling","created":"2025-03-01","cited_by_count":189,"area":"lr"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2503.13939","title":"Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models","created":"2025-03-18","cited_by_count":144,"area":"lr"},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128,"area":"lr"},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","created":"2021-08-15","cited_by_count":118,"area":"lr"},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86,"area":"lr"},{"id":"2412.14446","title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","created":"2024-12-19","cited_by_count":86,"area":"lr"},{"id":"2410.20724","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","created":"2024-10-28","cited_by_count":80,"area":"lr"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67,"area":"lr"},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2309.15028","title":"Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding","created":"2023-09-26","cited_by_count":60,"area":"lr"},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57,"area":"lr"},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2412.13736","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","created":"2024-12-18","cited_by_count":46,"area":"lr"},{"id":"2401.06751","title":"The Unreasonable Effectiveness of Easy Training Data for Hard Tasks","created":"2024-01-12","cited_by_count":40,"area":"lr"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2401.15269","title":"Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models","created":"2024-01-27","cited_by_count":34,"area":"lr"},{"id":"2402.10980","title":"ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback","created":"2024-02-15","cited_by_count":33,"area":"lr"},{"id":"2212.09146","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","created":"2022-12-18","cited_by_count":32,"area":"lr"},{"id":"2412.11077","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval","created":"2024-12-15","cited_by_count":32,"area":"lr"},{"id":"2405.10316","title":"Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model","created":"2024-05-16","cited_by_count":30,"area":"lr"},{"id":"2305.01157","title":"Complex Logical Reasoning over Knowledge Graphs using Large Language Models","created":"2023-05-02","cited_by_count":28,"area":"lr"},{"id":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27,"area":"lr"},{"id":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27,"area":"lr"},{"id":"2306.06891","title":"Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models","created":"2023-06-12","cited_by_count":24,"area":"lr"},{"id":"2411.07107","title":"Training Neural Networks as Recognizers of Formal Languages","created":"2024-11-11","cited_by_count":24,"area":"lr"},{"id":"2210.15578","title":"GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs","created":"2022-10-27","cited_by_count":21,"area":"lr"},{"id":"2203.11130","title":"PACS: A Dataset for Physical Audiovisual CommonSense Reasoning","created":"2022-03-21","cited_by_count":18,"area":"lr"},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18,"area":"lr"},{"id":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"id":"2210.10105","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","created":"2022-10-18","cited_by_count":14,"area":"lr"},{"id":"2502.14083","title":"Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoral","created":"2025-02-19","cited_by_count":14,"area":"lr"},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2306.01707","title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","created":"2023-06-02","cited_by_count":12,"area":"lr"},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2507.17303","title":"A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model","created":"2025-07-23","cited_by_count":12,"area":"lr"},{"id":"2505.17923","title":"Language models can learn implicit multi-hop reasoning, but only if they have lots of training data","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2604.15259","title":"Stability and Generalization in Looped Transformers","created":"2026-04-16","cited_by_count":10,"area":"lr"},{"id":"2310.05797","title":"In-Context Explainers: Harnessing LLMs for Explaining Black Box Models","created":"2023-10-09","cited_by_count":9,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2511.12309","title":"Optimal Self-Consistency for Efficient Reasoning with Large Language Models","created":"2025-11-15","cited_by_count":9,"area":"lr"},{"id":"2209.15087","title":"Zero-shot visual reasoning through probabilistic analogical mapping","created":"2022-09-29","cited_by_count":8,"area":"lr"},{"id":"2312.07122","title":"Neural Reasoning About Agents' Goals, Preferences, and Actions","created":"2023-12-12","cited_by_count":8,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2505.19927","title":"TCP: a Benchmark for Temporal Constraint-Based Planning","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2510.24940","title":"SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens","created":"2025-10-28","cited_by_count":8,"area":"lr"},{"id":"2512.05955","title":"SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models","created":"2025-12-05","cited_by_count":8,"area":"lr"},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2601.15495","title":"Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2604.07955","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","created":"2026-04-09","cited_by_count":7,"area":"lr"},{"id":"2307.07734","title":"Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems","created":"2023-07-15","cited_by_count":6,"area":"lr"},{"id":"2308.10487","title":"Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees","created":"2023-08-21","cited_by_count":6,"area":"lr"},{"id":"2402.11903","title":"DiLA: Enhancing LLM Tool Learning with Differential Logic Layer","created":"2024-02-19","cited_by_count":6,"area":"lr"},{"id":"2410.04407","title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","created":"2024-10-06","cited_by_count":6,"area":"lr"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2601.06801","title":"Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2409.12865","title":"KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning","created":"2024-09-19","cited_by_count":5,"area":"lr"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2203.15704","title":"Fine-Grained Visual Entailment","created":"2022-03-29","cited_by_count":4,"area":"lr"},{"id":"2502.15132","title":"CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2503.21937","title":"Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming","created":"2025-03-27","cited_by_count":4,"area":"lr"},{"id":"2506.05188","title":"Counterfactual reasoning: an analysis of in-context emergence","created":"2025-06-05","cited_by_count":4,"area":"lr"},{"id":"2509.21443","title":"One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning","created":"2025-09-25","cited_by_count":4,"area":"lr"},{"id":"2510.21148","title":"How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation","created":"2025-10-24","cited_by_count":4,"area":"lr"},{"id":"2603.04124","title":"BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning","created":"2026-03-04","cited_by_count":4,"area":"lr"},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2411.01093","title":"TabVer: Tabular Fact Verification with Natural Logic","created":"2024-11-02","cited_by_count":3,"area":"lr"},{"id":"2502.08932","title":"On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2503.02343","title":"DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability","created":"2025-03-04","cited_by_count":3,"area":"lr"},{"id":"2503.10225","title":"Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA","created":"2025-03-13","cited_by_count":3,"area":"lr"},{"id":"2504.11889","title":"Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration","created":"2025-04-16","cited_by_count":3,"area":"lr"},{"id":"2508.11196","title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","created":"2025-08-15","cited_by_count":3,"area":"lr"},{"id":"2511.00879","title":"Assessing LLM Reasoning Steps via Principal Knowledge Grounding","created":"2025-11-02","cited_by_count":3,"area":"lr"},{"id":"2604.08571","title":"Robust Reasoning Benchmark","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2302.02117","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","created":"2023-02-04","cited_by_count":2,"area":"lr"},{"id":"2310.17451","title":"Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings","created":"2023-10-26","cited_by_count":2,"area":"lr"},{"id":"2401.09966","title":"Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection","created":"2024-01-18","cited_by_count":2,"area":"lr"},{"id":"2404.13847","title":"EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning","created":"2024-04-22","cited_by_count":2,"area":"lr"},{"id":"2501.00244","title":"Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking","created":"2024-12-31","cited_by_count":2,"area":"lr"},{"id":"2501.13397","title":"ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2505.19815","title":"Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective","created":"2025-05-26","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}