Research map / Vision-language and multimodal / Robot action and navigation
CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
Tianhang Wang, Xinhai Li, Fan Lu, Tianshi Gong, Jiankun Dong, Weiyi Xue, Sanqing Qu, Chenjia Bai, Guang Chen
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 CoNavBench | Qwen2.5-VL-3B · single-agent high-level | SR: 4.30 -> 12.90 | Improved |
| fine-tune on CoNavBench | Qwen2.5-VL-7B · single-agent step-by-step | SR: 1.26 -> 22.40 | Improved |
| use collaborative decomposition instead of single agent (step-by-step) | Qwen2.5-VL-3B finetuned · step-by-step tasks | SR: 29.65 -> 35.02 | Improved |
| use collaborative decomposition instead of single agent (step-by-step) | Qwen2.5-VL-7B finetuned · step-by-step tasks | SR: 22.40 -> 29.78 | Improved |
| use collaborative decomposition instead of single agent (high-level) | Qwen2.5-VL-3B finetuned · high-level tasks | SR: 12.90 -> 11.11 | Hurt |
| scale model from 3B to 7B after fine-tuning | Qwen2.5-VL · collaborative step-by-step | SR: 35.02 -> 29.78 | Hurt |
| use GPT-4o instead of 4o-mini as the generation agent (ablation) | NavCraft · collaborative task generation | success rate: 26.56% -> 46.75% | Improved |
| use Claude 3-5-haiku with collaboration for task generation (ablation) | NavCraft · task generation | collab success rate: 3.90% | Mixed |
Closest papers by meaning
- Iterative Vision-and-Language Navigation (CVPR 2023 · similarity 0.90)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.90)
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.89)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.88)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.88)
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration (AAAI 2025 · similarity 0.88)
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.
