Reward Atlas
All field guidesEsc to close
Sign in
LLM / AgenticPublicPublishedv1.0Advanced

SQL-Detective-v1

A multi-turn agent answers analytics questions by querying a read-only SQLite sandbox. Tool use, verifiable rewards, 12-turn budget. Maintained by Bhaskar & Jaswanth · updated 28 Aug 2026.

Dataset
2,400 q · 12 DBs
Action
tool call | final answer
Turn cap
12
Best baseline
GRPO-7B 61.4%
07

Configuration

Arguments

nametypedefaultdescription
splitstr"train""train" (2,000) or "eval" (400)
max_turnsint12Turn budget before truncation
query_timeout_sfloat5.0Per-query timeout inside the sandbox
row_limitint200Rows returned per query
partial_creditboolTrueDisable to make reward strictly binary
Guide details
Version
Type
LLM / Agentic
API
OpenEnv
License
Apache-2.0
Seeds
3
Domains
tool-usedatacoding
Install
pip install reward-atlas-sql-detective

Issue with this step? Suggest an edit