{"total":68,"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":"2507.21892","title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","created":"2025-07-29","cited_by_count":52,"area":"rag"},{"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":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2506.01710","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","created":"2025-06-02","cited_by_count":18,"area":"lr"},{"id":"2511.17190","title":"AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale","created":"2025-11-21","cited_by_count":17,"area":null},{"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":"2506.04494","title":"SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2507.22478","title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","created":"2025-07-30","cited_by_count":10,"area":null},{"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":"2505.12380","title":"Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward","created":"2025-05-18","cited_by_count":7,"area":"alignment"},{"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":"2510.12831","title":"MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training","created":"2025-10-12","cited_by_count":5,"area":"agents"},{"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":"2510.07309","title":"Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"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":"2603.16161","title":"SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation","created":"2026-03-17","cited_by_count":3,"area":"agents"},{"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":"2606.14211","title":"Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"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":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"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":"2511.11770","title":"Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"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":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.03742","title":"ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2604.15646","title":"FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2506.11986","title":"Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2508.03094","title":"Augmenting Continual Learning of Diseases with LLM-Generated Visual Concepts","created":"2025-08-05","cited_by_count":1,"area":null},{"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":"2510.27630","title":"Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training","created":"2025-10-31","cited_by_count":1,"area":"agents"},{"id":"2602.15564","title":"Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.06736","title":"SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.04719","title":"Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL","created":"2026-05-06","cited_by_count":1,"area":null},{"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":"2606.23693","title":"EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2608.02876","title":"BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"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":"2512.09441","title":"Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model","created":"2025-12-10","cited_by_count":0,"area":"mllm"},{"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":"2601.10318","title":"Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis","created":"2026-01-15","cited_by_count":0,"area":"synth"},{"id":"2605.03465","title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.21792","title":"Residual Skill Optimization for Text-to-SQL Ensembles","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.22843","title":"Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model","created":"2026-05-13","cited_by_count":0,"area":"distill"},{"id":"2606.01246","title":"SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.03327","title":"CAPER: Clause-Aligned Process Supervision for Text-to-SQL","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.05906","title":"ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.16603","title":"VeriGraph: Towards Verifiable Data-Analytic Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2607.20489","title":"EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL","created":"2026-06-04","cited_by_count":0,"area":null},{"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":"2608.00485","title":"SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning","created":"2026-08-01","cited_by_count":0,"area":"agents"},{"id":"2608.29345","title":"BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.04697","title":"SQL-Zero: Self-Evolving Text-to-SQL","created":"2026-09-04","cited_by_count":0,"area":"synth"},{"id":"2609.18135","title":"DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.24186","title":"LIMIT: Less Is More for Instruction Tuning in Text-to-SQL","created":"2026-09-21","cited_by_count":0,"area":null},{"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}