mlsanityData to 7 Oct 2026

RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution

arXiv 2601.01126 ↗First posted 3 Jan 2026cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

We present RoboPhD, a system where AI agents autonomously conduct research to improve Text-to-SQL performance. RoboPhD implements a closed-loop evolution cycle with two coordinated components: a SQL Generation agent composed of a database analysis script and SQL generation instructions, and an Evolution agent that designs new versions based on performance feedback. Central to the framework is an ELO-based selection mechanism enabling survival-of-the-fittest dynamics while handling non-transitivity in performance. Starting from a naive 70-line baseline, RoboPhD evolves agents through iterative cross-pollination, discovering effective techniques without any external guidance on the Text-to-SQL domain. Our best agent, evolved to 1500 lines over 18 iterations, autonomously discovered strategies such as size-adaptive database analysis that adjusts depth based on schema complexity and SQL generation patterns for column selection, evidence interpretation, and aggregation. Evolution provides the largest gains on cheaper models: while we improve by 2.3 points over a strong Claude Opus 4.5 naive baseline, we show an improvement of 8.9 points over the weaker Claude Haiku model. This enables 'skip a tier' deployment: evolved Haiku exceeds naive Sonnet accuracy, and evolved Sonnet exceeds naive Opus, both at lower cost. The full system achieves 73.67% accuracy on the BIRD test set, demonstrating that AI can autonomously build a strong agentic system with only a trivial human-provided starting point.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 3 Jan 2026.

Builds on

22 of 38 references.

References · 22

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  3. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  4. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  5. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  6. 2023Large Language Models as Optimizerscited by 830
  7. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  8. 2017Population Based Training of Neural Networkscited by 351
  9. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  10. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  11. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  12. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
10 more
  1. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  2. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  3. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  4. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  5. 2016CMA-ES for Hyperparameter Optimization of Deep Neural Networkscited by 47
  6. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  7. 2025Automatic Metadata Extraction for Text-to-SQLcited by 25
  8. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learningcited by 15
  9. 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applicationscited by 15
  10. 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuningcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  2. 2026RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgetscited by 2
  3. 2026From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SQL-Zero: Self-Evolving Text-to-SQL
  2. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
  3. 2026Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL
  4. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
  5. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
  6. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
  7. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQL
  8. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation