{"total":89,"rows":[{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076,"area":"lr"},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350,"area":"lr"},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238,"area":"lr"},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196,"area":"lr"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127,"area":"lr"},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116,"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":"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":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70,"area":"lr"},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2402.17644","title":"Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data","created":"2024-02-27","cited_by_count":63,"area":"lr"},{"id":"2401.06915","title":"DocFinQA: A Long-Context Financial Reasoning Dataset","created":"2024-01-12","cited_by_count":60,"area":"lr"},{"id":"2311.09805","title":"DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents","created":"2023-11-16","cited_by_count":45,"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":"2305.18742","title":"Graph Reasoning for Question Answering with Triplet Retrieval","created":"2023-05-30","cited_by_count":34,"area":"lr"},{"id":"2210.12374","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","created":"2022-10-22","cited_by_count":29,"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":"2402.11194","title":"Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering","created":"2024-02-17","cited_by_count":25,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"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":"2401.13223","title":"TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data","created":"2024-01-24","cited_by_count":19,"area":"lr"},{"id":"2412.01230","title":"GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering","created":"2024-12-02","cited_by_count":18,"area":"lr"},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2210.10105","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","created":"2022-10-18","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":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2409.11724","title":"TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning","created":"2024-09-18","cited_by_count":10,"area":"lr"},{"id":"2505.00016","title":"Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning","created":"2025-04-23","cited_by_count":9,"area":"lr"},{"id":"2408.12337","title":"Fine-tuning Smaller Language Models for Question Answering over Financial Documents","created":"2024-08-22","cited_by_count":8,"area":"lr"},{"id":"2505.18961","title":"Weaver: Interweaving SQL and LLM for Table Reasoning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2308.10585","title":"Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning","created":"2023-08-21","cited_by_count":7,"area":"lr"},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2412.12567","title":"FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning","created":"2024-12-17","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2401.10744","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","created":"2024-01-19","cited_by_count":6,"area":"lr"},{"id":"2309.12669","title":"HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering","created":"2023-09-22","cited_by_count":5,"area":"lr"},{"id":"2411.03877","title":"EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning","created":"2024-11-06","cited_by_count":5,"area":"lr"},{"id":"2505.19563","title":"TabularMath: Understanding Math Reasoning over Tables with Large Language Models","created":"2025-05-26","cited_by_count":5,"area":"lr"},{"id":"2506.16123","title":"FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning","created":"2025-06-19","cited_by_count":5,"area":"lr"},{"id":"2603.11339","title":"FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles","created":"2026-03-11","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2310.14435","title":"Retrieval-Augmented Chain-of-Thought in Semi-structured Domains","created":"2023-10-22","cited_by_count":4,"area":"lr"},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","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":"2506.18421","title":"TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models","created":"2025-06-23","cited_by_count":3,"area":"lr"},{"id":"2511.11233","title":"STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models","created":"2025-11-14","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":"2603.29232","title":"Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs","created":"2026-03-31","cited_by_count":3,"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":"2509.21284","title":"Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.11031","title":"LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2511.18177","title":"Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models","created":"2025-11-22","cited_by_count":2,"area":"lr"},{"id":"2603.04663","title":"Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2411.18915","title":"MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications","created":"2024-11-28","cited_by_count":1,"area":"lr"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2601.19827","title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","created":"2026-01-27","cited_by_count":1,"area":"lr"},{"id":"2601.21157","title":"Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial Reasoning","created":"2026-01-29","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":"2604.17433","title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2604.20755","title":"V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.25188","title":"DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs","created":"2026-05-24","cited_by_count":1,"area":"lr"},{"id":"2605.29168","title":"Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2609.33052","title":"BudgetVerify: Budget-Tiered Verification for Financial QA","created":"2026-09-27","cited_by_count":1,"area":"lr"},{"id":"2405.13044","title":"Case-Based Reasoning Approach for Solving Financial Question Answering","created":"2024-05-18","cited_by_count":0,"area":"lr"},{"id":"2601.01825","title":"CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning","created":"2026-01-05","cited_by_count":0,"area":"lr"},{"id":"2603.08291","title":"A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning","created":"2026-03-09","cited_by_count":0,"area":"lr"},{"id":"2604.20273","title":"ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2604.25907","title":"How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum","created":"2026-04-28","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":"2607.01661","title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","created":"2026-07-02","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":"2607.22633","title":"Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2607.28661","title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.11047","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.18534","title":"FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.27506","title":"Thinking Costs Tokens: When More Structure is Worth the Price","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.27919","title":"From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2608.28402","title":"VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.30705","title":"The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32492","title":"Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.36651","title":"FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.17869","title":"ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.17937","title":"MERIT: Multimodal Evidence Reasoning over Image Tables","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}