# TRACE: Temporal Reasoning over Context and Evidence for Activity Recognition in Smart Homes

arXiv: https://arxiv.org/abs/2605.02841 · HTML: https://mlsanity.com/paper/2605.02841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 102 references that are in the map.
- First posted on arXiv 4 May 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 13 of 13)

- [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://mlsanity.com/paper/2502.04128/) (2025)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [A Survey of Deep Causal Models and Their Industrial Applications](https://mlsanity.com/paper/2209.08860/) (2022)
- [RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition](https://mlsanity.com/paper/2512.08984/) (2025)
- [Large Language Model-Guided Semantic Alignment for Human Activity Recognition](https://mlsanity.com/paper/2410.00003/) (2024)
- [Bridging the gap between natural user expression with complex automation programming in smart homes](https://mlsanity.com/paper/2408.12687/) (2024)
- [Using LLMs for Late Multimodal Sensor Fusion for Activity Recognition](https://mlsanity.com/paper/2509.10729/) (2025)
- [Know Thy Neighbors: A Graph Based Approach for Effective Sensor-Based Human Activity Recognition in Smart Homes](https://mlsanity.com/paper/2311.09514/) (2023)
- [Knowledge Distillation for LLM-Based Human Activity Recognition in Homes](https://mlsanity.com/paper/2601.07469/) (2026)
- [Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence](https://mlsanity.com/paper/2601.08241/) (2026)
- [Multidimensional Human Activity Recognition With Large Language Model: A Conceptual Framework](https://mlsanity.com/paper/2410.03546/) (2024)
- [On-device Large Multi-modal Agent for Human Activity Recognition](https://mlsanity.com/paper/2512.19742/) (2025)
- [LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition](https://mlsanity.com/paper/2512.22385/) (2025)

## Abstract (arXiv)

Human activity recognition (HAR) in smart homes remains challenging because many daily activities exhibit similar local sensor patterns, while minimally intrusive sensing provides sparse and ambiguous observations. As a result, methods based on short temporal or event windows often fail to capture the broader temporal and behavioral context needed for reliable activity understanding. We present TRACE (Temporal Reasoning over Context and Evidence), a contextual activity recognition framework for smart homes that integrates multi-source sensor evidence with user-specific contextual priors to improve activity interpretation. Rather than treating recognition as a local classification problem, TRACE leverages contextual reasoning to resolve ambiguities, reduce fragmented predictions, and infer more semantically specific activities. We evaluate TRACE on public benchmarks and in a deployment study conducted in our smart-home environment. Results show that TRACE improves recognition accuracy for semantically complex activities, produces more temporally coherent predictions that better align with user-specific routines, and maintains robust performance under cross-domain transfer and missing-modality conditions. These findings demonstrate the value of contextual reasoning for advancing smart-home HAR.