# EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent

arXiv: https://arxiv.org/abs/2607.13792 · HTML: https://mlsanity.com/paper/2607.13792/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 31)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models](https://mlsanity.com/paper/2410.10818/) (2024)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [My View is the Best View: Procedure Learning from Egocentric Videos](https://mlsanity.com/paper/2207.10883/) (2022)
- [CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities](https://mlsanity.com/paper/2312.14556/) (2023)
- [VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI](https://mlsanity.com/paper/2410.11623/) (2024)
- [AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant](https://mlsanity.com/paper/2203.04203/) (2022)
- [Proactive Assistant Dialogue Generation from Streaming Egocentric Videos](https://mlsanity.com/paper/2506.05904/) (2025)
- [LongVideoAgent: Multi-Agent Reasoning with Long Videos](https://mlsanity.com/paper/2512.20618/) (2025)
- [Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement](https://mlsanity.com/paper/2508.04025/) (2025)
- [STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos](https://mlsanity.com/paper/2301.00794/) (2023)
- [United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos](https://mlsanity.com/paper/2311.03550/) (2023)
- [EgoVLM: Policy Optimization for Egocentric Video Understanding](https://mlsanity.com/paper/2506.03097/) (2025)
- [ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding](https://mlsanity.com/paper/2410.22211/) (2024)
- [CaRe-Ego: Contact-aware Relationship Modeling for Egocentric Interactive Hand-object Segmentation](https://mlsanity.com/paper/2407.05576/) (2024)
- [EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts](https://mlsanity.com/paper/2410.05343/) (2024)
- [ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction](https://mlsanity.com/paper/2504.01472/) (2025)
- [Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport](https://mlsanity.com/paper/2507.15540/) (2025)
- [EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization](https://mlsanity.com/paper/2506.14356/) (2025)
- [GUI-C2: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning](https://mlsanity.com/paper/2605.30884/) (2026)

## Built on by (most cited first, 2 of 2)

- [EgoErrorVQA: Assess Egocentric Comprehension Capabilities through Procedural Errors for Ego-Agentic AI](https://mlsanity.com/paper/2608.24134/) (2026)
- [INSPECT: Learning Robot View Selection from Assistant Use](https://mlsanity.com/paper/2609.20615/) (2026)

## Abstract (arXiv)

Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understanding and largely overlook complex key-step-level reasoning under the widely used video question answering (VQA) paradigm for MLLMs. Such capabilities are crucial for building procedural AI assistants deployable on wearable devices. To bridge this gap, we introduce the Egocentric Procedural Understanding VQA task (EgoProceVQA), which systematically evaluates egocentric procedural reasoning abilities of current MLLMs and agents through six types of key-step-centric questions. Furthermore, we develop EgoProceGen, a data generation platform that efficiently constructs QA data tailored to different question types. Based on this platform, we build a benchmark with 3,600 questions, four common procedural scenarios, and 31 everyday procedural tasks. Evaluations on EgoProceVQA show that existing MLLMs and agents still have substantial room for improvement in procedural understanding. Therefore, we further propose EgoProceAgent, a self-skill-exploration agentic framework. We design a generic tool library for procedural understanding and a standardized sub-skill library shared across tools and models, enabling self-exploration without ground-truth supervision. By exploring how to compose and select sub-skills, the agent discovers effective skill strategies for diverse problems, and attains state-of-the-art performance among open-source models on multiple tasks. Together, our benchmark, generation platform, and agentic framework establish a unified foundation for EgoProceVQA. Project page: https://z1oong.github.io/EgoProceVQA/.