Projects

This section contains training pipelines built with rLLM for domain-specific applications.

Available Projects

💰 FinQA

Train a specialized 4B financial analysis agent that outperforms Qwen3-235B (59.7% vs 51.4%) and rivals Gemini 2.5 Pro (60.6%) on Snorkel AI's expert-curated agentic financial benchmark. Train with RL to perform multi-step financial reasoning over SEC 10-K filings.