EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking
Organizations: Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence
Abstract
Active embodied question answering requires agents to acquire evidence through viewpoint changes and physical interaction. The central challenge is to avoid undirected interaction: taking plausible actions without specifying what evidence they should reveal for answering the question. Action plans and accumulated histories alone can leave the informational purpose of an interaction implicit. We introduce EviSeek, a training-free framework that makes question-derived evidence demands explicit acquisition objectives, linking observation-conditioned actions and selectively retained evidence to the information the agent seeks. On 3,436 ESI-Bench questions, EviSeek improves accuracy over the Single-model agent by 7.1 percentage points with Qwen3-VL-32B and 3.7 points with Gemini 3.1 Pro, while improving visual-support-weighted accuracy and reducing mean token usage. These findings support making the informational purpose of interaction explicit, with action selection and evidence retention organized around what the agent needs to learn to answer the question.
Figures & tables
| Category | #Q | Qwen3-VL-32B | Gemini 3.1 Pro | ||||
|---|---|---|---|---|---|---|---|
| Passive | Single-model | EviSeek | Passive | Single-model | EviSeek | ||
| Perceptual Grounding | 750 | 58.0 | 62.3 | 78.5 | 75.9 | 80.0 | 84.9 |
| Physical Structure | 254 | 55.9 | 52.4 | 50.4 | 62.2 | 69.3 | 70.5 |
| Physical Dynamics | 150 | 32.7 | 65.3 | 53.3 | 40.0 | 64.0 | 68.0 |
| Specular Reflection | 300 | 49.3 | 44.0 | 44.3 | 47.7 | 54.0 | 49.7 |
| Spatial Relations | 781 | 27.9 | 28.3 | 46.2 | 27.8 | 36.9 | 46.6 |
| Method | Steps | Calls | Tokens | Images |
|---|---|---|---|---|
| Qwen3-VL-32B | ||||
| Single-model | 18.79 | 20.55 | 139,380 | 5.91 |
| EviSeek | 18.11 | 12.69 | 76,470 | 4.39 |
| Gemini 3.1 Pro | ||||
| Single-model | 10.71 | 12.15 | 86,887 | 5.24 |
| EviSeek | 12.17 | 10.05 | 74,839 | 4.38 |
| Variant | Acc | Acc |
|---|---|---|
| EviSeek | 52.7 | — |
| w/o evidence demands | 46.6 | |
| w/o evidence board | 47.6 | |
| w/o selective retention | 47.4 |
| Method | ||||
|---|---|---|---|---|
| Blind | — | 53.79 | — | — |
| Single-model | 19.48 | 40.09 | 18.66 | 6.42 |
| Fine-EQA | 49.92 | 67.10 | 33.15 | 5.60 |
| EviSeek (nav.) | 41.60 | 63.09 | 37.77 | 6.37 |
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
| Subcategory | #Q | Qwen | Gemini | ||||
|---|---|---|---|---|---|---|---|
| Passive | Single-model | EviSeek | Passive | Single-model | EviSeek | ||
| Perceptual Grounding | |||||||
| View Hallucination | 437 | 55.8 | 59.5 | 78.9 | 77.6 | 82.8 | 88.1 |
| Partial Occlusion | 95 | 22.1 | 50.5 | 86.3 | 54.7 | 74.7 | 85.3 |
| Material Transparency | 218 | 78.0 | 72.9 | 74.3 | 81.7 | 76.6 | 78.4 |
| Physical Structure | |||||||
| Subcategory | #Q | Qwen3-VL-32B | Gemini 3.1 Pro | ||
|---|---|---|---|---|---|
| Single-model | EviSeek | Single-model | EviSeek | ||
| Perceptual Grounding | |||||
| View Hallucination | 437 | 52.86 | 67.16 | 75.51 | 79.18 |
| Partial Occlusion | 95 | 37.89 | 35.26 | 64.21 | 60.53 |
| Material Transparency | 218 | 56.19 | 69.72 | 65.60 | 69.72 |
| Physical Structure | |||||
| Action | ESI | EXP |
| Locomotion | ||
| move_forward | ✓ | ✓ |
| move_backward | ✓ | — |
| move_left / move_right | ✓ | — |
| move_up / move_down | ✓ | — |
| Perception | ||
| Intent | Description | Compiled actions | ESI | EXP |
|---|---|---|---|---|
| FACE | Orient toward a bearing | ✓ | ✓ | |
| APPROACH | Close in on a visible target | ✓ | ✓ | |
| GOTO | Reposition to a seen landmark | ✓ | ✓ | |
| SWEEP | Scan the surroundings in a bounded fan | ✓ | ✓ | |
| ORBIT | Shift azimuth around a visible target | ✓ | — | |
| RISE_TOPDOWN | Rise for an overhead layout view | ✓ | — |
| Baseline | Metric | Qwen3-VL-32B | Gemini 3.1 Pro | ||||||
|---|---|---|---|---|---|---|---|---|---|
| 95% CI | 95% CI | ||||||||
| Passive | Acc | ||||||||
| Single-model | Acc | ||||||||
| Configuration | Acc | Tokens / step | Expl. steps |
|---|---|---|---|
| Single-model | 46.71 | 6,127 | 9.3 |
| EviSeek intent | 50.84 | 12,863 | 13.3 |
| EviSeek | 53.08 | 5,591 | 17.5 |
Embodied QA
Embodied question answering studies how agents use perception, memory, and action to answer questions grounded in the physical world.
See all 43 papers