You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition
On the map: LLM agents and tool use → Multimodal and embodied agents
Abstract (arXiv)
Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a complementary view inspired by human cognitive learning: people learn activities by remembering examples, forming rules, and repairing mistakes, not by backpropagating. This proposed tool implements AHL for HAR: a learning-time agent reasons over sensor protocols, proposes executable heuristic policies, records repair traces, and exports an LLM-free policy for edge deployment. We focus on the HAR benchmark family and provide an end-to-end workflow from dataset observation to edge-oriented export. On eleven HAR datasets evaluated so far, AHL policies reach strong executable-policy performance while remaining inspectable, editable, and replayable footnotehttps://github.com/zhaxidele/ahl-ts-studio.
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 5 of its 30 references that are in the map. First posted on arXiv 13 Sep 2026.
Builds on
5 of 30 references.
References · 5
- 2020Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunitiescited by 126
- 2023Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardwarecited by 27
- 2023Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOcited by 15
- 2025TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devicescited by 8
- 2026Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlookcited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment
- 2026OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition
- 2025On-device Large Multi-modal Agent for Human Activity Recognition
- 2025RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
- 2023Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
- 2026SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition
- 2025Towards Generalizable Human Activity Recognition: A Survey
- 2021A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation