# Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation

arXiv: https://arxiv.org/abs/2510.20310 · HTML: https://mlsanity.com/paper/2510.20310/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [IQA: Visual Question Answering in Interactive Environments](https://mlsanity.com/paper/1712.03316/) (2017)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought](https://mlsanity.com/paper/2405.16473/) (2024)
- [Multi-Target Embodied Question Answering](https://mlsanity.com/paper/1904.04686/) (2019)
- [Explore until Confident: Efficient Exploration for Embodied Question Answering](https://mlsanity.com/paper/2403.15941/) (2024)
- [Neural Modular Control for Embodied Question Answering](https://mlsanity.com/paper/1810.11181/) (2018)
- [Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage](https://mlsanity.com/paper/2412.15606/) (2024)
- [VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models](https://mlsanity.com/paper/2405.16919/) (2024)
- [GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering](https://mlsanity.com/paper/2412.14480/) (2024)
- [Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger](https://mlsanity.com/paper/2502.12961/) (2025)
- [Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering](https://mlsanity.com/paper/2503.11117/) (2025)
- [TANGO: Training-free Embodied AI Agents for Open-world Tasks](https://mlsanity.com/paper/2412.10402/) (2024)
- [EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering](https://mlsanity.com/paper/2410.20263/) (2024)
- [MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI](https://mlsanity.com/paper/2506.23563/) (2025)
- [VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering](https://mlsanity.com/paper/1908.04950/) (2019)
- [Memory-Centric Embodied Question Answering](https://mlsanity.com/paper/2505.13948/) (2025)

## Built on by (most cited first, 3 of 3)

- [ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception](https://mlsanity.com/paper/2607.10180/) (2026)
- [Automating the Design of Embodied Agent Architectures](https://mlsanity.com/paper/2606.30111/) (2026)
- [Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation](https://mlsanity.com/paper/2608.30396/) (2026)

## Abstract (arXiv)

Embodied Question Answering (EQA) requires agents to explore 3D environments to obtain observations and answer questions related to the scene. Existing methods leverage VLMs to directly explore the environment and answer questions without explicit thinking or planning, which limits their reasoning ability and results in excessive or inefficient exploration as well as ineffective responses. In this paper, we introduce ToolEQA, an agent that integrates external tools with multi-step reasoning, where external tools can provide more useful information for completing the task, helping the model derive better exploration directions in the next step of reasoning and thus obtaining additional effective information. This enables ToolEQA to generate more accurate responses with a shorter exploration distance. To enhance the model's ability for tool-usage and multi-step reasoning, we further design a novel EQA data generation pipeline that automatically constructs large-scale EQA tasks with reasoning trajectories and corresponding answers. Based on the pipeline, we collect the EQA-RT dataset that contains about 18K tasks, divided into a training set EQA-RT-Train, and two test sets EQA-RT-Seen (scenes overlapping with the training set) and EQA-RT-Unseen (novel scenes). Experiments on EQA-RT-Seen and EQA-RT-Unseen show that ToolEQA improves the success rate by 9.2~20.2% over state-of-the-art baselines, while outperforming the zero-shot ToolEQA by 10% in success rate. In addition, ToolEQA also achieves state-of-the-art performance on the HM-EQA, OpenEQA, and EXPRESS-Bench datasets, demonstrating its generality. Our homepage see https://tooleqa.github.io.