README.md

metadata

title: TRUST-SQL
emoji: 🔎
colorFrom: gray
colorTo: indigo
sdk: gradio
sdk_version: 6.27.0
app_file: app.py
python_version: '3.12'
startup_duration_timeout: 1h
pinned: false
license: apache-2.0
short_description: Text-to-SQL over unknown schemas, via tool use
models:
  - AIJian/TrustSQL-8B

TRUST-SQL — Text-to-SQL over unknown schemas

Demo of AIJian/TrustSQL-8B, from TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas (Jian et al., 2026). Code: JaneEyre0530/TrustSQL.

Unlike ordinary text-to-SQL demos, the schema is never put in the prompt. The model is given only the database name, the question, and a single read-only SQL tool, and has to discover the schema itself by following the authors' four-phase action protocol:

1. explore_schema — issue metadata queries (PRAGMA, sqlite_master, sampling rows)
2. propose_schema — write down the tables/columns/joins it has actually verified
3. generate_sql — draft the answer query and execute it to check it works
4. confirm_answer — emit the final SQL

The agent may loop back at any point. The full trajectory (reasoning, tool calls, observations) is streamed into the transcript so you can watch the schema being discovered.

Implementation notes

• The system prompt is trustsql_eval/prompt_template.txt, copied verbatim from the authors' repo.
• The user message reproduces the exact **Task Configuration** / **Database Engine** / **Database** / **External Knowledge** / **User Question** format found in AIJian/TrustSQL-data.
• The turn loop, progress prefixes, <schema> acknowledgement, malformed-output feedback and observation truncation (2048 tokens) are ported from trustsql_eval/message_processor.py.
• Sampling defaults match trustsql_eval/main.py (temperature 0.7, top-p 0.9).
• Deviation: WITH is added to the SELECT / PRAGMA / EXPLAIN allow-list so CTE answers can be executed. Every query still runs over a read-only SQLite connection.
• Runs on ZeroGPU with plain transformers generation rather than the vLLM path used for the paper's benchmarks, so it is slower than the reported latency figures.

Credits & licensing

• Model and code: Apache-2.0, © the TRUST-SQL authors (Meituan / BUPT).
• Bundled sample databases and the example questions + evidence hints are from the BIRD dev set (bird-bench.github.io), licensed CC BY-SA 4.0; SQLite files mirrored via prem-research/birdbench.

@article{jian2026trustsql,
  title  = {TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas},
  author = {Jian, Ai and Zhang, Xiaoyun and Du, Wanrou and Ruan, Jingqing and Pei, Jiangbo and Zhang, Weipeng and Zeng, Ke and Cai, Xunliang},
  journal= {arXiv preprint arXiv:2603.16448},
  year   = {2026}
}