用市场机制验证每条事实，让金融推理更精准可靠。
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
- 将问题拆成原子事实，由专家代理买卖判断真伪
- 在5个基准上最高达86.9%准确率，关键任务超70%
- 适合需要高精度财务与表格推理的场景
金融与表格问答不仅需流畅推理，更要求答案严格基于具体事实、公式、单位、符号和量级。一个误读单元格或错误运算可能产生看似合理却错误的结果。我们提出 extsc{MOCA-Agent}，一种基于声明的代码代理系统，以声明级验证替代自由形式的多代理辩论。系统将每个问题分解为带类型的原子声明，让专业交易员代理买入或卖出这些声明，通过订单清算生成置信度加权的接受/拒绝决策，并基于市场支持的证据合成可执行的Python程序。代码感知验证器检查程序的执行性、结构一致性及常见金融推理错误，最多一次市场感知修复。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上， extsc{MOCA-Agent}使用固定Qwen3.6-27B骨干模型取得优异表现，包括FinQA上78.3%、FinanceMath上76.0%、MultiHiertt上71.2%、ESGenius上86.9%，以及FinChart-Bench平均85.6%的准确率。结果表明，在原子声明层面聚合证据，而非整个答案，能显著提升高风险数值推理的鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。