Model Releases
You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition
arXiv:2609.16065v1 Announce Type: cross Abstract: Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a c
arXiv:2609.16065v1 Announce Type: cross Abstract: 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 footnote{https://github.com/zhaxidele/ahl-ts-studio}.
Related
- STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
- Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition
- QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition
Source: arXiv cs.AI | 2026-09-16