# Continuous improvement of language agents on DS-1000 StreamBench (32 held-out episodes)

Source: [Continuous improvement of language agents on DS-1000 StreamBench (32 held-out episodes)](<https://www.sota2.com/research/sota/continuous-improvement-of-language-agents-on-ds-1000-streambench-32-held-out-episodes>)

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

Data updated: 2026-06-09T09:13:48.705Z

Evaluation of language agents focusing on their ability to continuously improve performance across 32 held-out episodes within the DS-1000 environment, measured by success rates like pass@4.

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 | Continuous improvement of language agents |
| Dataset (including any stated split) | DS-1000 StreamBench (32 held-out episodes) |
| Metric | Pass@4 |
| 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

- [Pass@4](<https://www.sota2.com/research/sota/continuous-improvement-of-language-agents-on-ds-1000-streambench-32-held-out-episodes.md?metric=Pass%404>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@4 | Result date | Report paper |
| --- | --- | --- | --- |
| Memory w/ MEMOPILOT | 56.3 | Not recorded | 6a279e2890966ade919bf7e5 |
| Full History | 52.5 | Not recorded | 6a279e2890966ade919bf7e5 |
| No Memory | 50 | Not recorded | 6a279e2890966ade919bf7e5 |
| Memory w/ DeepSeek-V3.2 | 50 | Not recorded | 6a279e2890966ade919bf7e5 |
| Memory w/ Qwen2.5-14B | 48.8 | Not recorded | 6a279e2890966ade919bf7e5 |

### Memory w/ MEMOPILOT

Pass@4: 56.3. Result ID: 6a27d8dcfbc373592c24d56a.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

Recorded evaluation configuration: {"Memory Strategy":"MEMOPILOT","Execution Agent":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### Full History

Pass@4: 52.5. Result ID: 6a27d8dcfbc373592c24d567.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

Recorded evaluation configuration: {"Memory Strategy":"Full History","Execution Agent":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### No Memory

Pass@4: 50. Result ID: 6a27d8dcfbc373592c24d566.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

Recorded evaluation configuration: {"Memory Strategy":"No Memory","Execution Agent":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### Memory w/ DeepSeek-V3.2

Pass@4: 50. Result ID: 6a27d8dcfbc373592c24d568.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

Recorded evaluation configuration: {"Memory Strategy":"DeepSeek-V3.2","Execution Agent":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

### Memory w/ Qwen2.5-14B

Pass@4: 48.8. Result ID: 6a27d8dcfbc373592c24d569.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e2890966ade919bf7e5.md>)

Recorded evaluation configuration: {"Memory Strategy":"Qwen2.5-14B","Execution Agent":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction.

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