Research map / Large language models / Alignment and preferences
ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation
Jiho Kim, Junseong Choi, Woosog Chay, Daeun Kyung, Yeonsu Kwon, Yohan Jo, Edward Choi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add DPO preference training on user-agent ratings (ablation) | ProPerAssistant vs ARS Memory · ProPerSim, 32 personas | avg score (0-4) | Improved |
| put reward scores in the prompt (ARS Memory) instead of omitting them (ablation) | AR Memory · ProPerSim, 32 personas | avg score (0-4) | Improved |
| add action-recommendation history without scores (AR Memory) to No Memory (ablation) | No Memory · ProPerSim, 32 personas | avg score (0-4) | No clear effect |
| train with DPO over 14 days | ProPerAssistant · ProPerSim, 32 personas | successful intervention rate (%): 51.06 -> 71.51 | Improved |
| train with DPO over 14 days | ProPerAssistant · ProPerSim, 32 personas | avg score (0-4): 2.2 -> 3.3 | Improved |
| train with DPO over 14 days | ProPerAssistant · ProPerSim, 32 personas | recommendations per hour: 24 -> 6 | Improved |
| train with DPO over 14 days | ProPerAssistant · ProPerSim, persona 3 (complex preferences) | avg score (0-4): 1.93 -> 2.53 | Mixed |
| train with DPO over 14 days | ProPerAssistant · Personal Preference criterion | criterion score: 0.77 -> 0.83 on recommended actions | No clear effect |
| target personas low in extraversion | ProPerAssistant · ProPerSim Big Five analysis | score improvement | Mixed |
| target personas low in openness | ProPerAssistant · ProPerSim Big Five analysis | score improvement | Mixed |
Closest papers by meaning
- PersonalLLM: Tailoring LLMs to Individual Preferences (ICLR 2025 · similarity 0.86)
- PersonaVLM: Long-Term Personalized Multimodal LLMs (CVPR 2026 · similarity 0.86)
- Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction (AAAI 2026 · similarity 0.86)
- HYDRA: Model Factorization Framework for Black-Box LLM Personalization (NeurIPS 2024 · similarity 0.86)
- ContextAgent: Context-Aware Proactive LLM Agents with Open-world Sensory Perceptions (NeurIPS 2025 · similarity 0.85)
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward (NeurIPS 2025 · similarity 0.85)
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.
