# Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

arXiv: https://arxiv.org/abs/2403.17359 · HTML: https://mlsanity.com/paper/2403.17359/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [Knowledge-Aware Language Model Pretraining](https://mlsanity.com/paper/2007.00655/) (2020)
- [Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models](https://mlsanity.com/paper/2305.14623/) (2023)
- [Distilling Semantic Priors from SAM to Efficient Image Restoration Models](https://mlsanity.com/paper/2403.16368/) (2024)
- [Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection](https://mlsanity.com/paper/2403.13335/) (2024)
- [Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts](https://mlsanity.com/paper/2403.13786/) (2024)
- [When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs](https://mlsanity.com/paper/2309.14488/) (2023)

## Built on by (most cited first, 27 of 27)

- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners](https://mlsanity.com/paper/2504.14239/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse](https://mlsanity.com/paper/2503.18470/) (2025)
- [Improving Retrieval Augmented Language Model with Self-Reasoning](https://mlsanity.com/paper/2407.19813/) (2024)
- [RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models](https://mlsanity.com/paper/2404.12065/) (2024)
- [Enhance Image-to-Image Generation with LLaVA-generated Prompts](https://mlsanity.com/paper/2406.01956/) (2024)
- [Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action](https://mlsanity.com/paper/2405.17822/) (2024)
- [Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?](https://mlsanity.com/paper/2410.01353/) (2024)
- [MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains](https://mlsanity.com/paper/2603.00873/) (2026)
- [Decoupled Alignment for Robust Plug-and-Play Adaptation](https://mlsanity.com/paper/2406.01514/) (2024)
- [Advanced AI Framework for Enhanced Detection and Assessment of Abdominal Trauma: Integrating 3D Segmentation with 2D CNN and RNN Models](https://mlsanity.com/paper/2407.16165/) (2024)
- [Do Code LLMs Understand Design Patterns?](https://mlsanity.com/paper/2501.04835/) (2025)
- [SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets](https://mlsanity.com/paper/2510.19247/) (2025)
- [Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models](https://mlsanity.com/paper/2409.06223/) (2024)
- [AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.01586/) (2025)
- [FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning](https://mlsanity.com/paper/2601.19001/) (2026)
- [Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety](https://mlsanity.com/paper/2508.03864/) (2025)
- [FairReason: Balancing Reasoning and Social Bias in MLLMs](https://mlsanity.com/paper/2507.23067/) (2025)
- [Masked Generative Policy for Robotic Control](https://mlsanity.com/paper/2512.09101/) (2025)
- [FinRobot: Generative Business Process AI Agents for Enterprise Resource Planning in Finance](https://mlsanity.com/paper/2506.01423/) (2025)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations](https://mlsanity.com/paper/2603.17305/) (2026)
- [Attention Sinks and Outliers in Attention Residuals](https://mlsanity.com/paper/2605.17887/) (2026)
- [MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation](https://mlsanity.com/paper/2510.04057/) (2025)
- [PDF Retrieval Augmented Question Answering](https://mlsanity.com/paper/2506.18027/) (2025)

## Abstract (arXiv)

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.