# Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models Source: [Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:58:44.561Z Authors: Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu Published: 2024-03-26T03:51:01.000Z ## Abstract We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable \`Plug-and-Play' actions for retrieving real-time information from heterogeneous sources. We also propose a multi-reference faith score (MRFS) to verify and resolve conflicts in the answers. Empirically, we exploit both public benchmarks and a Web3 case study to demonstrate the capability of CoA over other methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Expert Explanation Evaluation on Web3 Case 100](): Expert Evaluation of Explanations and Reasoning Trajectories; Web3 Case 100 questions from real users' question history; Coverage: 2.9. ## Original sources and implementation [Original paper]() [PDF]()