# Agent Routing on AppWorld 14-agent pool

Source: [Agent Routing on AppWorld 14-agent pool](<https://www.sota2.com/research/sota/agent-routing-on-appworld-14-agent-pool>)

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

Data updated: 2026-06-15T07:28:33.375Z

Evaluation of agent routing performance on the specific 14-agent pool subset of the AppWorld environment, measured by Score and Success rate.

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 | Agent Routing |
| Dataset (including any stated split) | AppWorld 14-agent pool |
| Metric | Score |
| 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

- [Score](<https://www.sota2.com/research/sota/agent-routing-on-appworld-14-agent-pool.md?metric=Score>): Higher is better; unit: PERCENT.

- [Success Rate](<https://www.sota2.com/research/sota/agent-routing-on-appworld-14-agent-pool.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| π\_oracle | 93.3 | Not recorded | 6a2f86e3d33dfb23e783be31 |
| π\_skill | 78.4 | Not recorded | 6a2f86e3d33dfb23e783be31 |
| π\_global | 74.3 | Not recorded | 6a2f86e3d33dfb23e783be31 |
| Δ\_or (oracle vs. global) | 19 | Not recorded | 6a2f86e3d33dfb23e783be31 |
| Δ\_sk (skill vs. global) | 4.1 | Not recorded | 6a2f86e3d33dfb23e783be31 |

### π\_oracle

Score: 93.3. Result ID: 6a2fa8d4fbc373592c2b953d.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

Recorded evaluation configuration: {"Router":"oracle"}. This record does not assert independent reproduction.

### π\_skill

Score: 78.4. Result ID: 6a2fa8d4fbc373592c2b953c.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

Recorded evaluation configuration: {"Router":"skill"}. This record does not assert independent reproduction.

### π\_global

Score: 74.3. Result ID: 6a2fa8d4fbc373592c2b953b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

Recorded evaluation configuration: {"Router":"global"}. This record does not assert independent reproduction.

### Δ\_or (oracle vs. global)

Score: 19. Result ID: 6a2fa8d4fbc373592c2b953f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

Recorded evaluation configuration: {"Comparison":"oracle vs. global"}. This record does not assert independent reproduction.

### Δ\_sk (skill vs. global)

Score: 4.1. Result ID: 6a2fa8d4fbc373592c2b953e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f86e3d33dfb23e783be31.md>)

Recorded evaluation configuration: {"Comparison":"skill vs. global"}. This record does not assert independent reproduction.

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