{"total":102,"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":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"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":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77,"area":"lr"},{"id":"2401.06915","title":"DocFinQA: A Long-Context Financial Reasoning Dataset","created":"2024-01-12","cited_by_count":60,"area":"lr"},{"id":"2403.04483","title":"GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability","created":"2024-03-07","cited_by_count":58,"area":"lr"},{"id":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55,"area":"lr"},{"id":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2311.06602","title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","created":"2023-11-11","cited_by_count":28,"area":"lr"},{"id":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26,"area":"lr"},{"id":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24,"area":"lr"},{"id":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2410.14702","title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","created":"2024-10-06","cited_by_count":22,"area":"lr"},{"id":"2401.09042","title":"LLMs for Relational Reasoning: How Far are We?","created":"2024-01-17","cited_by_count":21,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2503.17604","title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","created":"2025-03-22","cited_by_count":20,"area":"lr"},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2505.24478","title":"Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning","created":"2025-05-30","cited_by_count":17,"area":"lr"},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2409.09239","title":"Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer","created":"2024-09-14","cited_by_count":16,"area":"lr"},{"id":"2506.02515","title":"FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning","created":"2025-06-03","cited_by_count":15,"area":"lr"},{"id":"2509.11420","title":"Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2306.10723","title":"Fine-tuning Large Enterprise Language Models via Ontological Reasoning","created":"2023-06-19","cited_by_count":14,"area":"lr"},{"id":"2401.15328","title":"Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance","created":"2024-01-27","cited_by_count":14,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2408.05093","title":"Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models","created":"2024-08-09","cited_by_count":12,"area":"lr"},{"id":"2310.04484","title":"Ada-Instruct: Adapting Instruction Generators for Complex Reasoning","created":"2023-10-06","cited_by_count":11,"area":"lr"},{"id":"2503.23513","title":"RARE: Retrieval-Augmented Reasoning Modeling","created":"2025-03-30","cited_by_count":11,"area":"lr"},{"id":"2402.11420","title":"Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction","created":"2024-02-18","cited_by_count":9,"area":"lr"},{"id":"2404.02934","title":"GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning","created":"2024-04-03","cited_by_count":9,"area":"lr"},{"id":"2406.15524","title":"Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization","created":"2024-06-21","cited_by_count":8,"area":"lr"},{"id":"2407.01212","title":"EconNLI: Evaluating Large Language Models on Economics Reasoning","created":"2024-07-01","cited_by_count":8,"area":"lr"},{"id":"2503.09326","title":"A Survey on Enhancing Causal Reasoning Ability of Large Language Models","created":"2025-03-12","cited_by_count":8,"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":"2508.03038","title":"Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree","created":"2025-08-05","cited_by_count":7,"area":"lr"},{"id":"2512.23515","title":"Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2506.04574","title":"Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2507.02954","title":"Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2407.19405","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","created":"2024-07-28","cited_by_count":5,"area":"lr"},{"id":"2510.15191","title":"Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"lr"},{"id":"2511.08616","title":"Reasoning on Time-Series for Financial Technical Analysis","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2602.22273","title":"FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2603.16112","title":"ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2603.19225","title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","created":"2026-03-19","cited_by_count":5,"area":"lr"},{"id":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","cited_by_count":4,"area":"lr"},{"id":"2509.23115","title":"RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility","created":"2025-09-27","cited_by_count":4,"area":"lr"},{"id":"2602.03130","title":"FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2603.07316","title":"FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets","created":"2026-03-07","cited_by_count":4,"area":"lr"},{"id":"2410.12464","title":"Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2606.29194","title":"AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution","created":"2026-06-28","cited_by_count":3,"area":"lr"},{"id":"2405.18073","title":"Towards Dialogues for Joint Human-AI Reasoning and Value Alignment","created":"2024-05-28","cited_by_count":2,"area":"lr"},{"id":"2502.05497","title":"DeepThink: Aligning Language Models with Domain-Specific User Intents","created":"2025-02-08","cited_by_count":2,"area":"lr"},{"id":"2502.13490","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2504.07997","title":"BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models","created":"2025-04-08","cited_by_count":2,"area":"lr"},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2510.13157","title":"Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2511.02451","title":"Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2603.15459","title":"Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning","created":"2026-03-16","cited_by_count":2,"area":"lr"},{"id":"2310.16713","title":"SkyMath: Technical Report","created":"2023-10-25","cited_by_count":1,"area":"lr"},{"id":"2412.11009","title":"Dual Traits in Probabilistic Reasoning of Large Language Models","created":"2024-12-15","cited_by_count":1,"area":"lr"},{"id":"2507.08339","title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"id":"2508.05009","title":"Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2509.12611","title":"Analogy-Driven Financial Chain-of-Thought (AD-FCoT): A Prompting Approach for Financial Sentiment Analysis","created":"2025-09-16","cited_by_count":1,"area":"lr"},{"id":"2510.01526","title":"One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2511.07070","title":"RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2512.24505","title":"Evaluating the Reasoning Abilities of LLMs on Underrepresented Mathematics Competition Problems","created":"2025-12-30","cited_by_count":1,"area":"lr"},{"id":"2603.01353","title":"Constructing Synthetic Instruction Datasets for Improving Reasoning in Domain-Specific LLMs: A Case Study in the Japanese Financial Domain","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2604.04300","title":"High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making","created":"2026-04-05","cited_by_count":1,"area":"lr"},{"id":"2604.16862","title":"Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.19633","title":"Time Series Augmented Generation for Financial Applications","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.12532","title":"AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2605.18843","title":"TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.21975","title":"Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2608.13129","title":"Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2608.30413","title":"DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2404.14395","title":"PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning?","created":"2024-04-22","cited_by_count":0,"area":"lr"},{"id":"2411.13599","title":"Can ChatGPT Overcome Behavioral Biases in the Financial Sector? Classify-and-Rethink: Multi-Step Zero-Shot Reasoning in the Gold Investment","created":"2024-11-19","cited_by_count":0,"area":"lr"},{"id":"2504.16505","title":"TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning","created":"2025-04-23","cited_by_count":0,"area":"lr"},{"id":"2507.13858","title":"InTraVisTo: Inside Transformer Visualisation Tool","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2509.16720","title":"Time to Revist Exact Match","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2510.05134","title":"Structuring Reasoning for Complex Rules Beyond Flat Representations","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2510.16686","title":"Investigating the Impact of Rationales for LLMs on Natural Language Understanding","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2512.22443","title":"Accounting Reasoning in Large Language Models: Concepts, Evaluation, and Empirical Analysis","created":"2025-12-27","cited_by_count":0,"area":"lr"},{"id":"2601.06707","title":"Evaluating Accounting Reasoning Capabilities of Large Language Models","created":"2026-01-10","cited_by_count":0,"area":"lr"},{"id":"2604.05135","title":"SenseAI: A Human-in-the-Loop Dataset for RLHF-Aligned Financial Sentiment Reasoning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.14214","title":"CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"id":"2605.24844","title":"Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning","created":"2026-05-24","cited_by_count":0,"area":"lr"},{"id":"2607.01388","title":"RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.16057","title":"Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2608.14094","title":"P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.26836","title":"SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}