{"total":130,"rows":[{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479,"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":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"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":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"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":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","cited_by_count":95,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"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":"2401.09003","title":"Augmenting Math Word Problems via Iterative Question Composing","created":"2024-01-17","cited_by_count":59,"area":"lr"},{"id":"2501.15089","title":"LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion","created":"2025-01-25","cited_by_count":50,"area":"lr"},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2311.01012","title":"COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances","created":"2023-11-02","cited_by_count":35,"area":"lr"},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33,"area":"lr"},{"id":"2208.13266","title":"JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents","created":"2022-08-28","cited_by_count":30,"area":"lr"},{"id":"2312.14878","title":"Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning","created":"2023-12-22","cited_by_count":30,"area":"lr"},{"id":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30,"area":"lr"},{"id":"2512.06690","title":"Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation","created":"2025-12-07","cited_by_count":30,"area":"lr"},{"id":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2402.09552","title":"STEER: Assessing the Economic Rationality of Large Language Models","created":"2024-02-14","cited_by_count":27,"area":"lr"},{"id":"2405.20774","title":"Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems","created":"2024-05-27","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":"2402.13212","title":"Soft Self-Consistency Improves Language Model Agents","created":"2024-02-20","cited_by_count":25,"area":"lr"},{"id":"2405.17402","title":"THREAD: Thinking Deeper with Recursive Spawning","created":"2024-05-27","cited_by_count":25,"area":"lr"},{"id":"2405.07938","title":"EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning","created":"2024-05-13","cited_by_count":22,"area":"lr"},{"id":"2410.18415","title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","created":"2024-10-24","cited_by_count":20,"area":"lr"},{"id":"2305.18869","title":"Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning","created":"2023-05-30","cited_by_count":19,"area":"lr"},{"id":"2410.12854","title":"TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees","created":"2024-10-10","cited_by_count":19,"area":"lr"},{"id":"2305.03742","title":"Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming","created":"2023-05-05","cited_by_count":18,"area":"lr"},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"area":"lr"},{"id":"2402.14382","title":"Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting","created":"2024-02-22","cited_by_count":17,"area":"lr"},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16,"area":"lr"},{"id":"2505.18706","title":"Steering LLM Reasoning Through Bias-Only Adaptation","created":"2025-05-24","cited_by_count":16,"area":"lr"},{"id":"2510.10103","title":"Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning","created":"2025-10-11","cited_by_count":16,"area":"lr"},{"id":"2205.12495","title":"ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection","created":"2022-05-25","cited_by_count":15,"area":"lr"},{"id":"2305.12563","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","created":"2023-05-21","cited_by_count":15,"area":"lr"},{"id":"2410.14725","title":"Rethinking Token Reduction for State Space Models","created":"2024-10-16","cited_by_count":15,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2502.14356","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","created":"2025-02-20","cited_by_count":14,"area":"lr"},{"id":"2504.06564","title":"Thinking Out Loud: Do Reasoning Models Know When They're Right?","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2501.19180","title":"Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning","created":"2025-01-31","cited_by_count":11,"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":"2507.15337","title":"Reasoning Models are Test Exploiters: Rethinking Multiple-Choice","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2505.22240","title":"BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2505.22756","title":"Decomposing Elements of Problem Solving: What \"Math\" Does RL Teach?","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2506.12301","title":"Unveiling Confirmation Bias in Chain-of-Thought Reasoning","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2210.11708","title":"Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2305.18373","title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models","created":"2023-05-28","cited_by_count":7,"area":"lr"},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2505.16886","title":"Don't \"Overthink\" Passage Reranking: Is Reasoning Truly Necessary?","created":"2025-05-22","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":"2604.08299","title":"SeLaR: Selective Latent Reasoning in Large Language Models","created":"2026-04-09","cited_by_count":7,"area":"lr"},{"id":"2402.14404","title":"On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe","created":"2024-02-22","cited_by_count":6,"area":"lr"},{"id":"2505.18087","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","created":"2025-05-23","cited_by_count":6,"area":"lr"},{"id":"2505.18555","title":"Unraveling Misinformation Propagation in LLM Reasoning","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2212.08686","title":"Evaluating Step-by-Step Reasoning through Symbolic Verification","created":"2022-12-16","cited_by_count":5,"area":"lr"},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"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":"2407.04212","title":"Smart Vision-Language Reasoners","created":"2024-07-05","cited_by_count":5,"area":"lr"},{"id":"2410.01545","title":"Lines of Thought in Large Language Models","created":"2024-10-02","cited_by_count":5,"area":"lr"},{"id":"2410.03122","title":"RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2509.13683","title":"Improving Context Fidelity via Native Retrieval-Augmented Reasoning","created":"2025-09-17","cited_by_count":5,"area":"lr"},{"id":"2510.00819","title":"Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2203.05186","title":"Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding","created":"2022-03-10","cited_by_count":4,"area":"lr"},{"id":"2410.01690","title":"Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2410.15484","title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs","created":"2024-10-20","cited_by_count":4,"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":"2512.11816","title":"Reinforcement Learning for Latent-Space Thinking in LLMs","created":"2025-11-26","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":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","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":"2305.13585","title":"Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs","created":"2023-05-23","cited_by_count":3,"area":"lr"},{"id":"2406.11035","title":"Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars","created":"2024-06-16","cited_by_count":3,"area":"lr"},{"id":"2406.14986","title":"Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models","created":"2024-06-21","cited_by_count":3,"area":"lr"},{"id":"2409.11783","title":"Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources","created":"2024-09-18","cited_by_count":3,"area":"lr"},{"id":"2411.13754","title":"Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios","created":"2024-11-20","cited_by_count":3,"area":"lr"},{"id":"2503.23487","title":"Large Language and Reasoning Models are Shallow Disjunctive Reasoners","created":"2025-03-30","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":"2508.11260","title":"UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs?","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":"2511.08983","title":"SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2210.06246","title":"CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm","created":"2022-10-12","cited_by_count":2,"area":"lr"},{"id":"2308.04811","title":"A Bipartite Graph is All We Need for Enhancing Emotional Reasoning with Commonsense Knowledge","created":"2023-08-09","cited_by_count":2,"area":"lr"},{"id":"2312.07886","title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","created":"2023-12-13","cited_by_count":2,"area":"lr"},{"id":"2411.15386","title":"Inducing Human-like Biases in Moral Reasoning Language Models","created":"2024-11-23","cited_by_count":2,"area":"lr"},{"id":"2412.08024","title":"TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection","created":"2024-12-11","cited_by_count":2,"area":"lr"},{"id":"2505.24643","title":"Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching","created":"2025-05-30","cited_by_count":2,"area":"lr"},{"id":"2509.05007","title":"Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework","created":"2025-09-05","cited_by_count":2,"area":"lr"},{"id":"2605.08776","title":"Reasoning Compression with Mixed-Policy Distillation","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2212.10292","title":"Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?","created":"2022-12-20","cited_by_count":1,"area":"lr"},{"id":"2309.07974","title":"A Data Source for Reasoning Embodied Agents","created":"2023-09-14","cited_by_count":1,"area":"lr"},{"id":"2410.01952","title":"TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking","created":"2024-10-02","cited_by_count":1,"area":"lr"},{"id":"2503.18908","title":"FFN Fusion: Rethinking Sequential Computation in Large Language Models","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2507.22940","title":"Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes","created":"2025-07-25","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}