arXiv AI
Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 27
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
arXiv:2604.08362v3 Announce Type: replace-cross Abstract: The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmark...
arXiv Computation and Language
Oct 5
CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking
The paper introduces Calibrated User Embeddings (CUE), a framework that encodes real user sessions into continuous representations and decodes them into persona commands to steer large language models (LLMs) as user simulators without additional training. CUE enables user-conditioned replay of past interactions and generates novel personas that better align with real-user success rates and failure patterns. Evaluations on the τ²‑Bench dataset show that CUE‑driven simulators commit fewer simulator‑attributed errors, more accurately reproduce real‑user failure modes, and maintain competitive user fidelity across various tasks and LLMs.
arXiv AI
Oct 2
NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video
NextMe-800 is an approximately 800‑hour first‑person video dataset collected from a single volunteer over 126 days, featuring 1 Hz images, gaze, and audio. The data are captioned at five hierarchical abstraction levels—from atomic actions to major activities—enabling personalized action anticipation as an open‑vocabulary K‑step sequence prediction task. The authors also introduce NextAct, a 1,500‑point benchmark that combines NextMe‑800 with the multi‑person EgoLife dataset, and evaluate models using an embedding‑based soft edit distance to assess how well personal behavior can be anticipated across abstraction levels and prediction horizons.
arXiv AI
Aug 3
SERUM: State Extraction and Refinement for User Modeling
arXiv:2607. 29181v1 Announce Type: cross Abstract: Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow.
arXiv Computation and Language
Oct 8
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
arXiv:2605.12894v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are uncle...
arXiv Machine Learning
Sep 18
ZeroHAT: Behavior-Conditioned Zero-Shot Human Activity Trace Generation
ZeroHAT is a new framework for generating synthetic human activity traces (HATs) in a target region without any real data from that region. It transfers behavioral patterns learned from real HATs in source regions and adapts them using publicly available contextual information about the target region. The system includes a consistency-aware intent extractor, a cross-region behavioral cloning module, and a behavior-conditioned activity realization module, and it outperforms the strongest baseline by 4.5–6.4× in downstream utility and improves fidelity by 15.6–40.8% across ten cities.