# LLM Agent Performance on AgentBoard BabyAI Compositional Stream

Source: [LLM Agent Performance on AgentBoard BabyAI Compositional Stream](<https://www.sota2.com/research/sota/llm-agent-performance-on-agentboard-babyai-compositional-stream>)

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

Data updated: 2026-06-02T13:37:54.166Z

Evaluation of LLM Agent performance on the AgentBoard BabyAI Compositional Stream dataset, measured by success rate (SR) and precision rate (PR) across two defined conditions (1- and 2-).

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 | LLM Agent Performance |
| Dataset (including any stated split) | AgentBoard BabyAI Compositional Stream |
| Metric | Success Rate (1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Success Rate (1)](<https://www.sota2.com/research/sota/llm-agent-performance-on-agentboard-babyai-compositional-stream.md?metric=Success%20Rate%20(1)>): Higher is better; unit: PERCENT.

- [Precision Rate (1)](<https://www.sota2.com/research/sota/llm-agent-performance-on-agentboard-babyai-compositional-stream.md?metric=Precision%20Rate%20(1)>): Higher is better; unit: PERCENT.

- [Success Rate (2)](<https://www.sota2.com/research/sota/llm-agent-performance-on-agentboard-babyai-compositional-stream.md?metric=Success%20Rate%20(2)>): Higher is better; unit: PERCENT.

- [Precision Rate (2)](<https://www.sota2.com/research/sota/llm-agent-performance-on-agentboard-babyai-compositional-stream.md?metric=Precision%20Rate%20(2)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Success Rate (1) | Result date | Report paper |
| --- | --- | --- | --- |
| MEMPROBE | 55.4 | Not recorded | 6a1e6451dbd7150506f859bd |
| ReMem | 51.8 | Not recorded | 6a1e6451dbd7150506f859bd |
| ReAct | 50 | Not recorded | 6a1e6451dbd7150506f859bd |
| ExpRAG | 37.5 | Not recorded | 6a1e6451dbd7150506f859bd |

### MEMPROBE

Success Rate (1): 55.4. Result ID: 6a1edc46fbc373592c1afb7f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6451dbd7150506f859bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6451dbd7150506f859bd.md>)

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

### ReMem

Success Rate (1): 51.8. Result ID: 6a1edc46fbc373592c1afb7e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6451dbd7150506f859bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927dae8d6b0dd3342930bb5.md>)

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

### ReAct

Success Rate (1): 50. Result ID: 6a1edc46fbc373592c1afb7c.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6451dbd7150506f859bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

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

### ExpRAG

Success Rate (1): 37.5. Result ID: 6a1edc46fbc373592c1afb7d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6451dbd7150506f859bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927dae8d6b0dd3342930bb5.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.