Research map / Multi-agent systems and games / Games and equilibria
Personalized Alert Agent for Optimal User Performance
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use fully personalized alerts instead of non-personalized alerts | maintenance alert agent · Spaceship game, 36 retained MTurk subjects | average user score: 5637 vs. 4756 | Helped |
| use fully personalized alerts instead of no alerts | maintenance alert agent · Spaceship game, 36 retained MTurk subjects | average user score: 5637 vs. 4833 | Helped |
| use non-personalized alerts instead of no alerts | maintenance alert agent · Spaceship game, 36 retained MTurk subjects | average user score: 4756 vs. 4833 | No clear effect |
| personalized alerts vs others including all subjects without exclusion | maintenance alert agent · Spaceship game, all subjects (no exclusion) | average user score: 3770 vs 3613 (NPA) and 2950 (no alert) | Helped |
| predict performance by exponential smoothing instead of previous second (ablation) | FPA performance predictor · Performance prediction, training data (20 subjects, 10-fold CV) | mean squared error: 1393 -> 649.5 | Helped |
| predict performance by exponential smoothing instead of full average (ablation) | FPA performance predictor · Performance prediction, training data (20 subjects, 10-fold CV) | mean squared error: 766.5 -> 649.5 | Helped |
| predict performance by exponential smoothing instead of moving window (ablation) | FPA performance predictor · Performance prediction, training data (20 subjects, 10-fold CV) | mean squared error: 767.1 -> 649.5 | Helped |
| non-personalized alerts increase maintenance actions relative to personalized alerts | NPA · Spaceship game, 36 retained MTurk subjects | maintenance actions per game: 7.8 vs 6.2 | Mixed |
| alerts from FPA vs no alerts on number of maintenance actions | FPA · Spaceship game, 36 retained MTurk subjects | maintenance actions per game: 6.2 vs 6.2 | No clear effect |
Closest papers by meaning
- Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations (NeurIPS 2026 · similarity 0.78)
- InfoPO: Information-Driven Policy Optimization for User-Centric Agents (ICML 2026 · similarity 0.78)
- Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface (ICLR 2025 · similarity 0.78)
- Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems (ICLR 2026 · similarity 0.78)
- AIR: Improving Agent Safety through Incident Response (ICML 2026 · similarity 0.78)
- The Partially Observable Off-Switch Game (AAAI 2025 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.