Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Alexa Arena: A User-Centric Interactive Platform for Embodied AI
Qiaozi Gao, Govind Thattai, Suhaila Shakiah, Xiaofeng Gao, Shreyas Pansare, Vasu Sharma, Gaurav S. Sukhatme, Hangjie Shi, Bofei Yang, Desheng Zhang, Lucy Hu, Karthika Arumugam and 13 more
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 question-answer (QA) dialog to input (ablation) | Neural-Symbolic model · validation missions | mission success rate (%): 18.19 -> 19.32 | Improved |
| add QA dialog to training and evaluation (ablation) | VL model · validation missions | mission success rate (%): 22.80 -> 34.20 | Improved |
| add QA dialog (ablation) | VL model · validation missions | average number of robot actions: 12.73 -> 8.82 | Improved |
| add QA dialog (ablation) | VL model · toggleDevice missions | mission success rate (%): 81.90 -> 81.90 | No clear effect |
| add QA dialog (ablation) | VL model · breakObject missions | mission success rate (%): 21.11 -> 41.11 | Improved |
| add QA dialog (ablation) | VL model · heat&deliver missions | mission success rate (%): 10.25 -> 28.20 | Improved |
| add QA dialog (ablation) | Neural-Symbolic model · freeze&deliver missions | mission success rate (%): 33.33 -> 25.00 | Hurt |
| add QA dialog (ablation) | Neural-Symbolic model · color&deliver missions | mission success rate (%): 0.00 -> 0.00 | No clear effect |
| give ground-truth visual observations to transformer (ablation) | Neural-Symbolic transformer · action and object prediction | fraction of missions fully correct (%): 71.3 -> 76.9 | Improved |
| train only mask head with ground-truth actions (ablation) | VL model · validation missions | mission success rate (%): 34.20 -> 71.89 | Improved |
Closest papers by meaning
- VirtualEnv: A Platform for Embodied AI Research (AAAI 2026 · similarity 0.85)
- LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents (NeurIPS 2025 · similarity 0.84)
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (ICLR 2024 · similarity 0.84)
- $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains (ICML 2026 · similarity 0.84)
- From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons (CVPR 2025 · similarity 0.83)
- Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence (NeurIPS 2025 · similarity 0.83)
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.
