LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement

arXiv:2610.14777 · cs.AI, cs.DB · Submitted 2026-10-10 · Read on arXiv

cs.AI, cs.DB

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/summerhare12/LYNX

Terminology

• Grounding — 1× in this paper · explained in 3 episodes

Sources

• CHESS: Contextual Harnessing for Efficient SQL Synthesis
• OpenAgents: An Open Platform for Language Agents in the Wild
• Querying Large Language Models with SQL
• TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
• ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems
• A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?
• LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment
• CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL
• ODIN: A NL2SQL Recommender to Handle Schema Ambiguity
• SQL-Encoder: Improving NL2SQL In-Context Learning Through a Context-Aware Encoder
• Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors
• Beyond Interestingness: Semantic and Context-Aware Natural Language Query Recommendations for Visual Data Analysis
• Evaluating Large Language Models Trained on Code
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
• AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
• Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms
• Code Llama: Open Foundation Models for Code
• Teaching Large Language Models to Self-Debug
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems