# Agentic Person Search (Spatial Reasoning) on Track 2 Spatial

Source: [Agentic Person Search (Spatial Reasoning) on Track 2 Spatial](<https://www.sota2.com/research/sota/agentic-person-search-spatial-reasoning-on-track-2-spatial>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T09:44:06.447Z

Evaluation of model performance on the Track 2 Spatial dataset, specifically focusing on Agentic Person Search capabilities requiring Spatial Reasoning, measured by TWS, Top-1, SRt@5, and AvgTs.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Agentic Person Search (Spatial Reasoning) |
| Dataset (including any stated split) | Track 2 Spatial |
| Metric | TWS |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [TWS](<https://www.sota2.com/research/sota/agentic-person-search-spatial-reasoning-on-track-2-spatial.md?metric=TWS>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/agentic-person-search-spatial-reasoning-on-track-2-spatial.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Success Rate @ 5](<https://www.sota2.com/research/sota/agentic-person-search-spatial-reasoning-on-track-2-spatial.md?metric=Success%20Rate%20%40%205>): Higher is better; unit: PERCENT.

- [Average Time](<https://www.sota2.com/research/sota/agentic-person-search-spatial-reasoning-on-track-2-spatial.md?metric=Average%20Time>): Lower is better; unit: TIME.

## Recorded results

| Method | TWS | Result date | Report paper |
| --- | --- | --- | --- |
| Oracle | 100 | Not recorded | 69df1bbf7d0172140ec7bb1b |
| ARGOS Agent | 38.3 | Not recorded | 69df1bbf7d0172140ec7bb1b |
| ARGOS Agent | 33.8 | Not recorded | 69df1bbf7d0172140ec7bb1b |
| ARGOS Agent | 32.3 | Not recorded | 69df1bbf7d0172140ec7bb1b |
| ARGOS Agent | 31.9 | Not recorded | 69df1bbf7d0172140ec7bb1b |

### Oracle

TWS: 100. Result ID: 69df5dd347f34ce924c882e2.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

Recorded evaluation configuration: {"Backbone":"Oracle"}. This record does not assert independent reproduction.

### ARGOS Agent

TWS: 38.3. Result ID: 69df5dd347f34ce924c882e6.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

Recorded evaluation configuration: {"Backbone":"Cl. Sonnet 4"}. This record does not assert independent reproduction.

### ARGOS Agent

TWS: 33.8. Result ID: 69df5dd347f34ce924c882e3.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### ARGOS Agent

TWS: 32.3. Result ID: 69df5dd347f34ce924c882e4.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### ARGOS Agent

TWS: 31.9. Result ID: 69df5dd347f34ce924c882e5.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbf7d0172140ec7bb1b.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5-mini"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.