# Multi-hop Retrieval-Augmented Generation on MHR NewsAgent Source

Source: [Multi-hop Retrieval-Augmented Generation on MHR NewsAgent Source](<https://www.sota2.com/research/sota/multi-hop-retrieval-augmented-generation-on-mhr-newsagent-source>)

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

Data updated: 2026-04-07T09:11:29.250Z

Evaluation of Multi-hop Retrieval-Augmented Generation performance using the MHR NewsAgent Source dataset, measured by Accuracy, Hallucination rate, and average Rounds.

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 | Multi-hop Retrieval-Augmented Generation |
| Dataset (including any stated split) | MHR NewsAgent Source |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/multi-hop-retrieval-augmented-generation-on-mhr-newsagent-source.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Hallucination Rate](<https://www.sota2.com/research/sota/multi-hop-retrieval-augmented-generation-on-mhr-newsagent-source.md?metric=Hallucination%20Rate>): Lower is better; unit: PERCENT.

- [Average Rounds](<https://www.sota2.com/research/sota/multi-hop-retrieval-augmented-generation-on-mhr-newsagent-source.md?metric=Average%20Rounds>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GoldRouter | 89.32 | Not recorded | 68fa76971e209131cea6dfa5 |
| RIRS | 84.75 | Not recorded | 68fa76971e209131cea6dfa5 |
| EfficientRAG | 81.8 | Not recorded | 68fa76971e209131cea6dfa5 |
| GoldRouter | 79.53 | Not recorded | 68fa76971e209131cea6dfa5 |
| Chameleon | 76.33 | Not recorded | 68fa76971e209131cea6dfa5 |
| RIRS | 71.91 | Not recorded | 68fa76971e209131cea6dfa5 |
| EfficientRAG | 66.8 | Not recorded | 68fa76971e209131cea6dfa5 |
| Chameleon | 54.52 | Not recorded | 68fa76971e209131cea6dfa5 |

### GoldRouter

Accuracy: 89.32. Result ID: 69d4ca3f47f34ce924bccc77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

Recorded evaluation configuration: {"Models":"Qwen"}. This record does not assert independent reproduction.

### RIRS

Accuracy: 84.75. Result ID: 69d4ca3f47f34ce924bccc7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

Recorded evaluation configuration: {"Models":"Qwen"}. This record does not assert independent reproduction.

### EfficientRAG

Accuracy: 81.8. Result ID: 69d4ca3f47f34ce924bccc75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74fc1e209131cea65162.md>)

Recorded evaluation configuration: {"Models":"Qwen"}. This record does not assert independent reproduction.

### GoldRouter

Accuracy: 79.53. Result ID: 69d4ca3f47f34ce924bccc78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

Recorded evaluation configuration: {"Models":"LLaMA"}. This record does not assert independent reproduction.

### Chameleon

Accuracy: 76.33. Result ID: 69d4ca3f47f34ce924bccc79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710e1e209131cea4eee8.md>)

[Implementation](<https://chameleon-llm.github.io/>)

Recorded evaluation configuration: {"Models":"Qwen"}. This record does not assert independent reproduction.

### RIRS

Accuracy: 71.91. Result ID: 69d4ca3f47f34ce924bccc7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

Recorded evaluation configuration: {"Models":"LLaMA"}. This record does not assert independent reproduction.

### EfficientRAG

Accuracy: 66.8. Result ID: 69d4ca3f47f34ce924bccc76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74fc1e209131cea65162.md>)

Recorded evaluation configuration: {"Models":"LLaMA"}. This record does not assert independent reproduction.

### Chameleon

Accuracy: 54.52. Result ID: 69d4ca3f47f34ce924bccc7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfa5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710e1e209131cea4eee8.md>)

[Implementation](<https://chameleon-llm.github.io/>)

Recorded evaluation configuration: {"Models":"LLaMA"}. This record does not assert independent reproduction.

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