Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations

• URL: http://arxiv.org/abs/2609.01257v1
• Date: Tue, 01 Sep 2026 13:51:11 GMT
• Title: Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations
• Abstract summary: We introduce a framework for evaluating behavioral fidelity in long-horizon activity simulations.<n>As a case study, we collect a 43-hour dataset of in-the-wild office activity.<n>We find that behavioral fidelity is not uniform across metrics.
• Score: 14.694276552510685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. While prior work has examined behavioral fidelity in survey responses and dialogue, longer-horizon real-world activity remains largely unexplored. We introduce a framework for evaluating behavioral fidelity in long-horizon activity simulations across temporal granularities and levels of analysis. As a case study, we collect a 43-hour multi-camera dataset of in-the-wild office activity and compare trace-derived conditioning mechanisms: persona descriptors, few-shot exemplars, and statistical transition and time-of-day priors. We find that behavioral fidelity is not uniform across metrics: statistical priors bring activity and sequence distributions closest to real behavior, yet over-fragment routines and suppress within-person variability. These findings motivate a more holistic evaluation that spans multiple metrics, temporal granularities, and levels of analysis.

Related papers

• Longitudinal Multimodal Sensing of Physical Activity and Well-Being in Older Adults [1.1744028458220426]
  We present a longitudinal multimodal study of 66 older adults conducted in real-world conditions.<n>We investigate how the alignment between sensed signals and target variables affects predictive performance.
  arXiv  Detail & Related papers  (2026-05-29T20:34:50Z)
• Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors [61.610957638373826]
  We introduce a method to measure the distributional gap between real and simulated user behaviors.<n>Given a dataset of real and simulated conversations, our method extracts representations of user behavior from each conversation.<n>We show that most simulators behave similarly, while a few stand apart.
  arXiv  Detail & Related papers  (2026-05-08T15:09:25Z)
• From Brain Models to Executable Digital Twins: Execution Semantics and Neuro-Neuromorphic Systems [51.82266520875928]
  This survey introduces physically constrained executability as a unifying perspective for comparing approaches at the level of execution.<n>I propose a taxonomy of execution regimes ranging from isolated offline models to coordinated co-simulation, to continuously executing digital twins sustained by online data.<n>The executability concept clarifies why accuracy alone is insufficient, and motivates an agenda centered on semantic interoperability, hybrid-time correctness, evaluation protocols, scalable assimilation, and safe closed-loop validation.
  arXiv  Detail & Related papers  (2026-04-15T07:34:46Z)
• Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces [81.41397370235102]
  We introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data.<n>We show that current models struggle to accurately simulate complex behaviors, with performance plateauing even as context windows expand.<n>This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.
  arXiv  Detail & Related papers  (2026-04-09T15:26:21Z)
• Evaluating Few-Shot Temporal Reasoning of LLMs for Human Activity Prediction in Smart Environments [1.411614392022118]
  Existing data-driven agent-based models struggle in low-data environments.<n>This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap.
  arXiv  Detail & Related papers  (2026-01-20T20:58:17Z)
• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention [52.159541540613915]
  We study how multi-head softmax attention models are trained to perform in-context learning on linear data.<n>Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution.
  arXiv  Detail & Related papers  (2025-03-17T02:00:49Z)
• How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation [30.713599131902566]
  We introduce BehaviorChain, the first benchmark for evaluating digital twins' ability to simulate continuous human behavior.<n> BehaviorChain comprises diverse, high-quality, persona-based behavior chains, totaling 15,846 distinct behaviors across 1,001 unique personas.<n> Comprehensive evaluation results demonstrated that even state-of-the-art models struggle with accurately simulating continuous human behavior.
  arXiv  Detail & Related papers  (2025-02-20T15:29:32Z)
• Dataset Bias in Human Activity Recognition [57.91018542715725]
  This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR.
  arXiv  Detail & Related papers  (2023-01-19T12:33:50Z)
• Multi-Timescale Modeling of Human Behavior [0.18199355648379031]
  We propose an LSTM network architecture that processes behavioral information at multiple timescales to predict future behavior. We evaluate our architecture on data collected in an urban search and rescue scenario simulated in a virtual Minecraft-based testbed.
  arXiv  Detail & Related papers  (2022-11-16T15:58:57Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.