MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
Researchers have developed MoCA-Agent, a novel code agent designed for robust financial and numerical reasoning. This system breaks down questions into atomic claims, uses specialist agents to trade these claims, and synthesizes an executable Python program from verified evidence. MoCA-Agent demonstrates strong performance on various benchmarks, including financial, tabular, and multimodal chart reasoning, by aggregating evidence at the claim level for improved accuracy. AI
IMPACT Enhances AI's ability to perform accurate financial and numerical reasoning by verifying claims at an atomic level.