# Agent Routing on AgentDNS runtime

Source: [Agent Routing on AgentDNS runtime](<https://www.sota2.com/research/sota/agent-routing-on-agentdns-runtime>)

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

Data updated: 2026-04-10T00:08:12.151Z

Evaluation of Agent Routing performance on the AgentDNS runtime dataset, measured by Action, Agent, Arg EM, Plan EM, Esc P, and Esc R.

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) | AgentDNS runtime |
| Metric | Action |
| 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

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

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

- [Arg EM](<https://www.sota2.com/research/sota/agent-routing-on-agentdns-runtime.md?metric=Arg%20EM>): Higher is better; unit: PERCENT.

- [Plan EM](<https://www.sota2.com/research/sota/agent-routing-on-agentdns-runtime.md?metric=Plan%20EM>): Higher is better; unit: PERCENT.

- [Esc P](<https://www.sota2.com/research/sota/agent-routing-on-agentdns-runtime.md?metric=Esc%20P>): Higher is better; unit: PERCENT.

- [Esc R](<https://www.sota2.com/research/sota/agent-routing-on-agentdns-runtime.md?metric=Esc%20R>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Action | Result date | Report paper |
| --- | --- | --- | --- |
| AgentGate | 94.25 | Not recorded | 69d732b37d0172140ec76c89 |
| Retrieve-rank | 92.5 | Not recorded | 69d732b37d0172140ec76c89 |
| Rule-based | 74 | Not recorded | 69d732b37d0172140ec76c89 |
| Tool-Calling | 24 | Not recorded | 69d732b37d0172140ec76c89 |

### AgentGate

Action: 94.25. Result ID: 69d83ec647f34ce924c036bd.

[Reporting paper](<https://www.sota2.com/research/paper/69d732b37d0172140ec76c89.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732b37d0172140ec76c89.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### Retrieve-rank

Action: 92.5. Result ID: 69d83ec647f34ce924c036bb.

[Reporting paper](<https://www.sota2.com/research/paper/69d732b37d0172140ec76c89.md>)

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

### Rule-based

Action: 74. Result ID: 69d83ec647f34ce924c036ba.

[Reporting paper](<https://www.sota2.com/research/paper/69d732b37d0172140ec76c89.md>)

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

### Tool-Calling

Action: 24. Result ID: 69d83ec647f34ce924c036bc.

[Reporting paper](<https://www.sota2.com/research/paper/69d732b37d0172140ec76c89.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction.

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