VerifiAgent：语言模型推理中的统一验证智能体
VerifiAgent: a Unified Verification Agent in Language Model Reasoning
AI总结：
VerifiAgent 是一个统一验证智能体，通过元验证与基于工具的自适应验证相结合，在多种推理任务中超越基线方法，并能以更低成本提升推理准确性和推理扩展效果。
摘要：
大型语言模型展现出卓越的推理能力，但往往会产生不可靠或错误的回答。现有的验证方法通常针对特定模型或受限于特定领域，需要大量计算资源，并且缺乏跨多种推理任务的可扩展性。为了解决这些局限性，我们提出了 VerifiAgent，一个统一的验证智能体，它整合了两个层次的验证：元验证（meta-verification），用于评估模型回答的完整性和一致性；以及基于工具的自适应验证，其中 VerifiAgent 根据推理类型（包括数学推理、逻辑推理或常识推理）自主选择合适的验证工具。这种自适应方法确保了在不同验证场景下的效率和鲁棒性。实验结果表明，VerifiAgent 在所有推理任务中均优于基线验证方法（例如演绎验证器、反向验证器）。此外，它还能通过利用验证结果的反馈进一步提高推理准确性。VerifiAgent 还可以有效应用于推理扩展（inference scaling），在数学推理领域，与现有的过程奖励模型相比，能够以更少的生成样本和成本取得更好的结果。代码可在 https://github.com/Jiuzhouh/VerifiAgent 获取。
英文摘要：
Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational resources and lacking scalability across diverse reasoning tasks. To address these limitations, we propose VerifiAgent, a unified verification agent that integrates two levels of verification: meta-verification, which assesses completeness and consistency in model responses, and tool-based adaptive verification, where VerifiAgent autonomously selects appropriate verification tools based on the reasoning type, including mathematical, logical, or commonsense reasoning. This adaptive approach ensures both efficiency and robustness across different verification scenarios. Experimental results show that VerifiAgent outperforms baseline verification methods (e.g., deductive verifier, backward verifier) among all reasoning tasks. Additionally, it can further enhance reasoning accuracy by leveraging feedback from verification results. VerifiAgent can also be effectively applied to inference scaling, achieving better results with fewer generated samples and costs compared to existing process reward models in the mathematical reasoning domain. Code is available at https://github.com/Jiuzhouh/VerifiAgent
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
