Finance Agent Benchmark

L3 OOD — Specialized Tools TaskPoolSet

Financial specialist tasks using EDGAR filing retrieval, web parsing, and domain-specific financial APIs. Requires understanding of financial documents and specialized tool invocation patterns not seen during training.

Tool Pool EDGAR / Web / Parse / Retrieve

Toolset Uniform

Protocol OpenAI Function Calling

Environment Stateless

Performance (Success Rate %)

Qwen3-8B (base)

2.0

EnvScaler-8B

14.0

DIVE-8B (SFT)

28.0

DIVE-8B (RL)

34.0

Base Best 8B Baseline DIVE (SFT) DIVE (RL)