Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3\%$ on FinQA, $76.0\%$ on FinanceMath, $71.2\%$ on MultiHiertt, $86.9\%$ on ESGenius, and $85.6\%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent.

翻译：金融和表格问答不仅要求流畅的推理能力，答案还必须严格基于可支撑的具体事实、公式、单位、符号和量级。单个单元格的误读或错误的操作步骤可能悄无声息地产生看似合理却错误的结论。我们提出\textsc{MOCA-Agent}，一种基于声明市场的代码智能体，用声明级验证取代了自由形式的多智能体辩论。该系统将每个问题分解为带类型的原子声明，委托专业交易者智能体买入或卖出这些声明，将其订单清算为置信度加权的接受/拒绝决策，并从市场支持的证据中综合出可执行的Python程序。随后，一个代码感知验证器检查程序的执行情况、结构一致性以及常见的金融推理错误，最多进行一次市场感知修复。在涵盖金融数值推理、通用表格推理、ESG问答和多模态图表推理的十个公开基准测试中，\textsc{MOCA-Agent}使用固定的Qwen3.6-27B主干模型取得了强劲性能，包括在FinQA上达$78.3\%$、在FinanceMath上达$76.0\%$、在MultiHiertt上达$71.2\%$、在ESGenius上达$86.9\%$，以及在FinChart-Bench上平均达$85.6\%$。这些结果表明，在原子声明层面（而非整体答案层面）聚合证据，可以提高高风险数值推理的鲁棒性。\footnote{代码和数据已公开：https://github.com/UBC-NLP/MoCA-Agent。}