# Search on Medium environment

Source: [Search on Medium environment](<https://www.sota2.com/research/sota/search-on-medium-environment>)

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

Data updated: 2026-03-04T08:24:07.756Z

Evaluation of agent performance on the Search task within the Medium environment setting, measured by Average completion time in timesteps.

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 | Search |
| Dataset (including any stated split) | Medium environment |
| Metric | Average Completion Time (timesteps) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Average Completion Time (timesteps)](<https://www.sota2.com/research/sota/search-on-medium-environment.md?metric=Average%20Completion%20Time%20(timesteps)>): Lower is better; unit: TIME.

## Recorded results

| Method | Average Completion Time (timesteps) | Result date | Report paper |
| --- | --- | --- | --- |
| COMRES-VLM | 104.25 | Not recorded | 68fa7be71e209131cea8b36d |
| AEP+DVC | 244.45 | Not recorded | 68fa7be71e209131cea8b36d |
| RACER | 244.73 | Not recorded | 68fa7be71e209131cea8b36d |

### COMRES-VLM

Average Completion Time (timesteps): 104.25. Result ID: 69a7eb566dbb7075b94cb4fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be71e209131cea8b36d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be71e209131cea8b36d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AEP+DVC

Average Completion Time (timesteps): 244.45. Result ID: 69a7eb566dbb7075b94cb4fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be71e209131cea8b36d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RACER

Average Completion Time (timesteps): 244.73. Result ID: 69a7eb566dbb7075b94cb4fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be71e209131cea8b36d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d731e209131cea39fdf.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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