# Action Learning on ALFRED (Q3)

Source: [Action Learning on ALFRED (Q3)](<https://www.sota2.com/research/sota/action-learning-on-alfred-q3>)

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

Data updated: 2026-06-01T10:15:07.709Z

Evaluation of model performance on Action Learning using the Q3 split of the ALFRED dataset, measured by Accuracy, Precision, Recall, and F1 score.

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 | Action Learning |
| Dataset (including any stated split) | ALFRED (Q3) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/action-learning-on-alfred-q3.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/action-learning-on-alfred-q3.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/action-learning-on-alfred-q3.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/action-learning-on-alfred-q3.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Affordance Routing (REIS) | 54.8 | Not recorded | 6a1d1238dbd7150506f841aa |
| RAG + Direct | 54.6 | Not recorded | 6a1d1238dbd7150506f841aa |
| CAG + Direct | 54.4 | Not recorded | 6a1d1238dbd7150506f841aa |
| Base + Direct | 50.1 | Not recorded | 6a1d1238dbd7150506f841aa |
| Base + Reasoning | 46.7 | Not recorded | 6a1d1238dbd7150506f841aa |

### Affordance Routing (REIS)

Accuracy: 54.8. Result ID: 6a1d5b87fbc373592c172e41.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

Recorded evaluation configuration: {"Avg Latency":"406.21 ms","Avg Output Tokens":"0"}. This record does not assert independent reproduction.

### RAG + Direct

Accuracy: 54.6. Result ID: 6a1d5b87fbc373592c172e40.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

Recorded evaluation configuration: {"Avg Latency":"1017.83 ms","Avg Output Tokens":"0"}. This record does not assert independent reproduction.

### CAG + Direct

Accuracy: 54.4. Result ID: 6a1d5b87fbc373592c172e3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

Recorded evaluation configuration: {"Avg Latency":"1027.44 ms","Avg Output Tokens":"0"}. This record does not assert independent reproduction.

### Base + Direct

Accuracy: 50.1. Result ID: 6a1d5b87fbc373592c172e3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

Recorded evaluation configuration: {"Avg Latency":"327.56 ms","Avg Output Tokens":"0"}. This record does not assert independent reproduction.

### Base + Reasoning

Accuracy: 46.7. Result ID: 6a1d5b87fbc373592c172e3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1238dbd7150506f841aa.md>)

Recorded evaluation configuration: {"Avg Latency":"43.59 sec","Avg Output Tokens":"230.8"}. This record does not assert independent reproduction.

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