# ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop

arXiv: https://arxiv.org/abs/2607.24770 · HTML: https://mlsanity.com/paper/2607.24770/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 9 Jun 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, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning](https://mlsanity.com/paper/2311.17842/) (2023)
- [The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose](https://mlsanity.com/paper/2007.00394/) (2020)
- [Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer](https://mlsanity.com/paper/2103.09712/) (2021)
- [AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents](https://mlsanity.com/paper/2401.12963/) (2024)
- [CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities](https://mlsanity.com/paper/2312.14556/) (2023)
- [WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition](https://mlsanity.com/paper/2304.05088/) (2023)
- [CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients](https://mlsanity.com/paper/2402.04620/) (2024)
- [Ads that Talk Back: Implications and Perceptions of Injecting Personalized Advertising into LLM Chatbots](https://mlsanity.com/paper/2409.15436/) (2024)
- [Guided Reality: Generating Visually-Enriched AR Task Guidance with LLMs and Vision Models](https://mlsanity.com/paper/2508.03547/) (2025)
- [ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly](https://mlsanity.com/paper/2509.02949/) (2025)
- [Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation](https://mlsanity.com/paper/2508.21399/) (2025)

## Abstract (arXiv)

Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task progress, reason about spatial state, and recover from errors while performing physical actions. Prior multimodal assistants have shown promise for procedural guidance, but most rely on cloud inference and fixed always-on perception, making them poorly suited to privacy-sensitive, latency-critical domestic settings. We present ProcAgent, a fully on-device, agentic, vision-based procedural assistant for real-time adaptive guidances on a single NVIDIA Jetson AGX Orin. ProcAgent uses a propose-and-verify architecture that combines low-latency continuous perception, a symbolic task graph, on-demand vision-language verification, and an LLM-based interaction agent. The system continuously proposes user progress, invokes expensive visual reasoning only when ambiguity or likely deviation arises, and supports both reactive question answering and proactive intervention with human-in-the- loop confirmation. We evaluate ProcAgent along four dimensions: perception accuracy, reasoning, task-level performance, and user experience. Despite running entirely on-device, the system maintains responsive interaction, resolving text-only queries in approximately 2 seconds and visually grounded queries in approximately 8 seconds. In a user study with 10 participants completing assembly tasks, ProcAgent receives positive ratings for comprehensibility, actionability, and privacy comfort. These results show that adaptive procedural assistance can be achieved entirely on edge hardware without sacrificing usability.