Get Started
Research questionHow can workplace agents interpret human activity traces at the temporal resolution each question requires?Fine-grained workplace events are too numerous for direct reasoning, while a single flattened summary can erase patterns that matter at a particular time horizon.
AI Agents
Machine Learning
Latest papersRecent research connected to this question, newest first.Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace AgentsThe evidence concerns human-attributed events from a large commercial productivity suite: 667 million events from 50,000 users across 100 organizations. It includes taxonomy recovery on a disjoint 2,000-user sample, held-out next-episode forecasting, and a controlled comparison of temporal resolutions.research paper · Sep 3, 2026
Related questions
How can LLM agents reuse execution traces without losing temporal and outcome-dependent behavior?How can agents find people across cameras from vague witness clues under spatial-temporal and turn constraints?How can we measure whether long-horizon tool-using agents query hidden state and execute stated plans?How can personalized dialogue agents keep evolving user personas traceable to supporting events during retrieval?
Home
Topics
Search
Library