Research map / Multi-agent systems and games / Human-AI and goal-conditioned
SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World
Jiaqi Zhang, Chen Gao, Liyuan Zhang, Quoc Viet Hung Nguyen, Hongzhi Yin
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 |
|---|---|---|---|
| fine-tune on SmartSpot channels instead of zero-shot transfer to unseen MEDICINE channel | SmartAgent · SmartSpot MEDICINE | Exp.Acc: 0.77 -> 0.71 | Hurt |
| fine-tune on SmartSpot channels instead of zero-shot transfer to unseen MEDICINE channel | SmartAgent · SmartSpot MEDICINE | Ele.Acc: 0.04 -> 0.64 | Improved |
| fine-tune on SmartSpot channels instead of zero-shot transfer to unseen MEDICINE channel | SmartAgent · SmartSpot MEDICINE | Imp.Acc: 0.14 -> 0.24 | Improved |
| two-stage COUT training (generate underlying-requirement thought) versus end-to-end training (ablation) | SmartAgent · SmartSpot FLIGHT and MOVIE | recommendation accuracy | Mixed |
| add personalized COUT training to GUI agent backbone | SmartAgent · ScreenSpot | grounding accuracy | No clear effect |
Closest papers by meaning
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.89)
- Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization (ICLR 2026 · similarity 0.88)
- Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence (NeurIPS 2025 · similarity 0.88)
- SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience (ICML 2026 · similarity 0.87)
- Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making (NeurIPS 2024 · similarity 0.87)
- Agent S: An Open Agentic Framework that Uses Computers Like a Human (ICLR 2025 · similarity 0.87)
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.
