{"total":166,"rows":[{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173,"area":"lr"},{"id":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2205.00445","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","created":"2022-05-01","cited_by_count":156,"area":"lr"},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2405.20139","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","created":"2024-05-30","cited_by_count":128,"area":"lr"},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84,"area":"lr"},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67,"area":"lr"},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2305.14825","title":"Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners","created":"2023-05-24","cited_by_count":63,"area":"lr"},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59,"area":"lr"},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"area":"lr"},{"id":"2305.19555","title":"Large Language Models Are Not Strong Abstract Reasoners","created":"2023-05-31","cited_by_count":53,"area":"lr"},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43,"area":"lr"},{"id":"2502.03671","title":"Advancing Reasoning in Large Language Models: Promising Methods and Approaches","created":"2025-02-05","cited_by_count":43,"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":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2407.12844","title":"metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models","created":"2024-07-04","cited_by_count":39,"area":"lr"},{"id":"2505.03970","title":"A Reasoning-Focused Legal Retrieval Benchmark","created":"2025-05-06","cited_by_count":37,"area":"lr"},{"id":"2304.05970","title":"Boosted Prompt Ensembles for Large Language Models","created":"2023-04-12","cited_by_count":36,"area":"lr"},{"id":"2303.14617","title":"Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases","created":"2023-03-26","cited_by_count":35,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2402.17887","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","created":"2024-02-27","cited_by_count":32,"area":"lr"},{"id":"2410.06237","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","created":"2024-10-08","cited_by_count":32,"area":"lr"},{"id":"2203.17271","title":"Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?","created":"2022-03-31","cited_by_count":31,"area":"lr"},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31,"area":"lr"},{"id":"2509.25681","title":"dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought","created":"2025-09-30","cited_by_count":30,"area":"lr"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","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":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2401.03991","title":"Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark","created":"2024-01-08","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":"2311.08206","title":"Human-Centric Autonomous Systems With LLMs for User Command Reasoning","created":"2023-11-14","cited_by_count":22,"area":"lr"},{"id":"2503.15952","title":"Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning","created":"2025-03-20","cited_by_count":21,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2305.02556","title":"Faithful Question Answering with Monte-Carlo Planning","created":"2023-05-04","cited_by_count":16,"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":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2305.01020","title":"Evaluating statistical language models as pragmatic reasoners","created":"2023-05-01","cited_by_count":15,"area":"lr"},{"id":"2310.14607","title":"Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications","created":"2023-10-23","cited_by_count":15,"area":"lr"},{"id":"2309.12485","title":"Studying and improving reasoning in humans and machines","created":"2023-09-21","cited_by_count":14,"area":"lr"},{"id":"2311.13148","title":"Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents","created":"2023-11-22","cited_by_count":14,"area":"lr"},{"id":"2403.14112","title":"Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations","created":"2024-03-21","cited_by_count":14,"area":"lr"},{"id":"2410.21411","title":"SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization","created":"2024-10-28","cited_by_count":14,"area":"lr"},{"id":"2506.05587","title":"MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2510.22710","title":"RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability","created":"2025-10-26","cited_by_count":14,"area":"lr"},{"id":"2402.06634","title":"SocraSynth: Multi-LLM Reasoning with Conditional Statistics","created":"2024-01-19","cited_by_count":13,"area":"lr"},{"id":"2502.08922","title":"Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models","created":"2025-02-13","cited_by_count":13,"area":"lr"},{"id":"2301.09723","title":"Mathematics, word problems, common sense, and artificial intelligence","created":"2023-01-23","cited_by_count":12,"area":"lr"},{"id":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"id":"2410.14690","title":"Rethinking VLMs and LLMs for Image Classification","created":"2024-10-03","cited_by_count":12,"area":"lr"},{"id":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2507.08960","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2210.06281","title":"TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs","created":"2022-10-12","cited_by_count":10,"area":"lr"},{"id":"2306.07536","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","created":"2023-06-13","cited_by_count":10,"area":"lr"},{"id":"2402.12091","title":"Do Large Language Models Understand Logic or Just Mimick Context?","created":"2024-02-19","cited_by_count":10,"area":"lr"},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9,"area":"lr"},{"id":"2410.21359","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games","created":"2024-10-28","cited_by_count":9,"area":"lr"},{"id":"2411.02344","title":"Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning","created":"2024-11-04","cited_by_count":9,"area":"lr"},{"id":"2507.11344","title":"Guiding LLM Decision-Making with Fairness Reward Models","created":"2025-07-15","cited_by_count":9,"area":"lr"},{"id":"2402.15420","title":"PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning","created":"2024-02-23","cited_by_count":8,"area":"lr"},{"id":"2407.00938","title":"MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education","created":"2024-07-01","cited_by_count":8,"area":"lr"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2410.17448","title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","created":"2024-10-22","cited_by_count":7,"area":"lr"},{"id":"2502.20758","title":"Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth","created":"2025-02-28","cited_by_count":7,"area":"lr"},{"id":"2507.02822","title":"SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model","created":"2025-07-03","cited_by_count":7,"area":"lr"},{"id":"2511.21861","title":"Towards a Foundation Model for Partial Differential Equations Across Physics Domains","created":"2025-11-26","cited_by_count":7,"area":"lr"},{"id":"2305.16602","title":"Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning","created":"2023-05-26","cited_by_count":6,"area":"lr"},{"id":"2309.16436","title":"Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving","created":"2023-09-28","cited_by_count":6,"area":"lr"},{"id":"2406.16061","title":"PORT: Preference Optimization on Reasoning Traces","created":"2024-06-23","cited_by_count":6,"area":"lr"},{"id":"2503.02670","title":"Multidimensional Consistency Improves Reasoning in Language Models","created":"2025-03-04","cited_by_count":6,"area":"lr"},{"id":"2203.05843","title":"An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation","created":"2022-03-11","cited_by_count":5,"area":"lr"},{"id":"2411.19589","title":"Can Large Language Models Reason about the Region Connection Calculus?","created":"2024-11-29","cited_by_count":5,"area":"lr"},{"id":"2503.21464","title":"Harnessing Chain-of-Thought Metadata for Task Routing and Adversarial Prompt Detection","created":"2025-03-27","cited_by_count":5,"area":"lr"},{"id":"2510.18184","title":"ActivationReasoning: Logical Reasoning in Latent Activation Spaces","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2501.10688","title":"Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers","created":"2025-01-18","cited_by_count":4,"area":"lr"},{"id":"2503.02379","title":"Teaching Metric Distance to Discrete Autoregressive Language Models","created":"2025-03-04","cited_by_count":4,"area":"lr"},{"id":"2503.11348","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","created":"2025-03-14","cited_by_count":4,"area":"lr"},{"id":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2510.18510","title":"Identity-Aware Large Language Models require Cultural Reasoning","created":"2025-10-21","cited_by_count":4,"area":"lr"},{"id":"2402.01602","title":"Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2505.14264","title":"AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin","created":"2025-05-20","cited_by_count":3,"area":"lr"},{"id":"2506.09566","title":"From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2508.07284","title":"\"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas","created":"2025-08-10","cited_by_count":3,"area":"lr"},{"id":"2509.19552","title":"iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning","created":"2025-09-23","cited_by_count":3,"area":"lr"},{"id":"2509.22472","title":"Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning","created":"2025-09-26","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}