Research map / Vision-language and multimodal / Robot action and navigation
Guide, Think, Act: Interactive Embodied Reasoning for Vision-Language-Action Model
Yiran Ling, Qing Lian, Jinghang Li, Qing Jiang, TianMing Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang
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 |
|---|---|---|---|
| remove vision CoT field (visual grounding) (ablation) | GTA-VLA · SimplerEnv WidowX | success rate (%): 81.2 -> 66.7 | Improved |
| add task CoT field (task decomposition) (ablation) | GTA-VLA · SimplerEnv WidowX | success rate (%): 68.8 -> 81.2 | Improved |
| add robot CoT field (motion sketch) (ablation) | GTA-VLA · SimplerEnv WidowX | success rate (%): 78.1 -> 81.2 | Improved |
| use structured CoT fields instead of free-form CoT (ablation) | GTA-VLA · SimplerEnv WidowX | success rate (%): 65.6 -> 81.2 | Improved |
| add visual point guide to dense instruction (ablation) | GTA-VLA · SimplerEnv-Plus distractor ambiguity | success rate (%): 37.5 -> 54.2 | Improved |
| add visual box guide to dense instruction (ablation) | GTA-VLA · SimplerEnv-Plus unseen object ambiguity | success rate (%): 27.8 -> 56.9 | Improved |
| add visual box guide instead of none on distractor ambiguity (ablation) | GTA-VLA · SimplerEnv-Plus distractor ambiguity | success rate (%): 37.5 -> 43.7 | Improved |
| add trace guide (ablation) | GTA-VLA · SimplerEnv-Plus obstacle-avoidance tasks | success rate (%): 27.8 -> 30.5 | Improved |
| add explicit spatial reasoning and guidance interface | GTA-VLA vs X-VLA · SimplerEnv-Plus OOD | avg success rate (%): 52.3 -> 61.4 | Improved |
| add spatial reasoning to policy | GTA-VLA vs X-VLA · LIBERO | avg success rate (%): 98.1 -> 98.6 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ThinkAct — ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning (NeurIPS 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning (NeurIPS 2025 · similarity 0.93)
- Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes (ICLR 2026 · similarity 0.91)
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025 · similarity 0.90)
- UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent (ICML 2025 · similarity 0.90)
- FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation (CVPR 2026 · similarity 0.90)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · 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.
