{"total":28,"rows":[{"id":"2505.00024","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","created":"2025-04-25","cited_by_count":68,"area":"lr"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2505.04671","title":"Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards","created":"2025-05-07","cited_by_count":27,"area":"lr"},{"id":"2506.01710","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","created":"2025-06-02","cited_by_count":18,"area":"lr"},{"id":"2505.13271","title":"CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning","created":"2025-05-19","cited_by_count":15,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","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":"2505.22942","title":"WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning","created":"2025-05-28","cited_by_count":8,"area":"lr"},{"id":"2601.17699","title":"SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL","created":"2026-01-25","cited_by_count":7,"area":"lr"},{"id":"2506.21575","title":"STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing","created":"2025-06-15","cited_by_count":5,"area":"lr"},{"id":"2505.20321","title":"BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases","created":"2025-05-23","cited_by_count":4,"area":"lr"},{"id":"2506.13404","title":"Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2603.16448","title":"TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2509.07159","title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","created":"2025-09-08","cited_by_count":2,"area":"lr"},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2511.22258","title":"Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques","created":"2025-11-27","cited_by_count":2,"area":"lr"},{"id":"2512.22364","title":"Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL","created":"2025-12-26","cited_by_count":2,"area":"lr"},{"id":"2508.17330","title":"Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering","created":"2025-08-24","cited_by_count":1,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2510.08896","title":"HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2606.06825","title":"Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2608.19794","title":"Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents","created":"2026-08-20","cited_by_count":1,"area":"lr"},{"id":"2601.05451","title":"RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning","created":"2026-01-09","cited_by_count":0,"area":"lr"},{"id":"2607.22622","title":"Learning When to Reason for Text-to-SQL via SFT and DPO","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2610.17309","title":"StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}