无需微调或闭源模型，多智能体协作高效解决复杂表格问答
Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
- 规划与编码双智能体协作，结合工具完成复杂推理
- 在四个基准上三个超越现有最优，两处媲美GPT-4性能
- 适合追求可复现性与低成本的表格问答研究者
复杂表格问答（TQA）旨在对以表格形式呈现的数据进行多步或多类别推理来回答问题。以往方法通过使用闭源大语言模型（LLMs）或微调的开源模型取得了显著性能。然而，微调需要高质量训练数据，成本高昂；而使用闭源模型则存在访问困难和可复现性问题。本文提出多智能体协作工具使用框架（MACT），既不依赖闭源模型也不需微调。MACT中，规划智能体与代码智能体协同工作，并利用外部工具完成任务。在四个TQA基准上的实验表明，MACT在其中三个基准上超越了现有最先进系统，在两个基准上表现接近使用闭源模型GPT-4的水平，且仅使用开源权重模型，无任何微调。我们进行了详尽分析，验证了MACT在复杂表格问答中多智能体协作的有效性。
原文摘要 · Abstract (English)
Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular form. Previous approaches demonstrated notable performance by leveraging either closed-source large language models (LLMs) or fine-tuned open-weight LLMs. However, fine-tuning LLMs requires high-quality training data, which is costly to obtain, and utilizing closed-source LLMs poses accessibility challenges and leads to reproducibility issues. In this paper, we propose Multi-Agent Collaboration with Tool use (MACT), a framework that requires neither closed-source models nor fine-tuning. In MACT, a planning agent and a coding agent that also make use of tools collaborate to answer questions. Our experiments on four TQA benchmarks show that MACT outperforms previous SoTA systems on three out of four benchmarks and that it performs comparably to the larger and more expensive closed-source model GPT-4 on two benchmarks, even when using only open-weight models without any fine-tuning. We conduct extensive analyses to prove the effectiveness of MACT's multi-agent collaboration in TQA.
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。