ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

Research Summary

Contribution Summary

• As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized.
• While recent advances have pushed forward proactivity and personalization individually, their combination remains underexplored.
• To bridge this gap, we introduce ProPerSim, a new task and simulation framework for developing assistants capable of making timely, personalized recommendations in realistic home scenarios.

Why It Matters For Eval

• In our simulation environment, a user agent with a rich persona interacts with the assistant, providing ratings on how well each suggestion aligns with its preferences and context.
• Built on ProPerSim, we propose ProPerAssistant, a retrieval-augmented, preference-aligned assistant that continually learns and adapts through user feedback.

Related Papers

• GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning Embedding Neighbor
• Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets Embedding Neighbor
• Oracular Programming: A Modular Foundation for Building LLM-Enabled Software Embedding Neighbor
• Modality-Guided Mixture of Graph Experts with Entropy-Triggered Routing for Multimodal Recommendation Embedding Neighbor
• ArXiv-to-Model: A Practical Study of Scientific LM Training Embedding Neighbor
• Prototype-Based Disentanglement for Controllable Dysarthric Speech Synthesis Embedding Neighbor
• PreScience: A Benchmark for Forecasting Scientific Contributions Embedding Neighbor
• Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning Embedding Neighbor
• IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning Embedding Neighbor
• BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning Tag Overlap
• Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Tag Overlap
• MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks Tag Overlap