FineStep adds step-level process rewards and credit assignment to tool-augmented Text-to-SQL, achieving 3.25% higher execution accuracy than GRPO on BIRD while cutting redundant tool calls.
A.2.3 Group Sequence Policy Optimization Group Sequence Policy Optimization (GSPO) (Zheng et al., 2025) addresses train- ing instability in large Mixture-of-Experts (MoE) models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
FineStep adds step-level process rewards and credit assignment to tool-augmented Text-to-SQL, achieving 3.25% higher execution accuracy than GRPO on BIRD while cutting redundant tool calls.