Research map / Vision-language and multimodal / Robot action and navigation
How Foundational Skills Influence VLM-based Embodied Agents: A Native Perspective
Bo Peng, Pi Bu, Keyu Pan, Xinrun Xu, Yingxiu Zhao, Miao Chen, Yang Du, Lin Li, Jun Song, Tong Xu
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 |
|---|---|---|---|
| give ground-truth perception text (instance segmentation templates) (ablation) | Claude-3.5-Sonnet · NativeEmbodied high-level tasks | success rate | No clear effect |
| give agent a LookAt primitive for alignment (ablation) | Claude-3.5-Sonnet · NativeEmbodied Search | success rate | Improved |
| allow teleport to visible target (navigation oracle) (ablation) | Claude-3.5-Sonnet · NativeEmbodied Exploration and Interaction | success rate | Improved |
| pre-decompose tasks into subtask sequences (ablation) | Claude-3.5-Sonnet · NativeEmbodied Exploration and Interaction | success rate | Improved |
| pre-decompose tasks into subtasks (ablation) | Claude-3.5-Sonnet · NativeEmbodied Search | success rate | No clear effect |
| enable thinking mode (ablation) | Gemini-2.5-Pro and Claude-4-Opus · NativeEmbodied Perception and Planning | success rate | Improved |
| enable thinking mode (ablation) | Gemini-2.5-Pro and Claude-4-Opus · NativeEmbodied Alignment and Navigation | success rate | Hurt |
Closest papers by meaning
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.93)
- BEAR: Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis (ICML 2026 · similarity 0.91)
- Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making (NeurIPS 2024 · similarity 0.91)
- UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent (ICML 2025 · similarity 0.90)
- PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (ICLR 2025 · similarity 0.90)
- VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments (CVPR 2026 · similarity 0.90)
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.
