# Multi-hop Question Answering on HotpotQA in-domain (test) Source: [Multi-hop Question Answering on HotpotQA in-domain (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:21:38.851Z Evaluation of model performance on the in-domain test split of the HotpotQA dataset for multi-hop question answering, measured using ACC\_R and ACC\_L metrics. 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 Question Answering | | Dataset (including any stated split) | HotpotQA in-domain (test) | | Metric | ACC\_R | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [ACC\_R](): Higher is better; unit: PERCENT. - [ACC\_L](): Higher is better; unit: PERCENT. ## Recorded results | Method | ACC\_R | Result date | Report paper | | --- | --- | --- | --- | | DLLM-Searcher | 60.4 | Not recorded | 698abbaac97a0b3e3b5ddffe | | R1Searcher | 58 | Not recorded | 698abbaac97a0b3e3b5ddffe | | WebSailor | 50.4 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Search-R1 | 49.6 | Not recorded | 698abbaac97a0b3e3b5ddffe | | IRCoT | 48.8 | Not recorded | 698abbaac97a0b3e3b5ddffe | | ReARTeR | 46.8 | Not recorded | 698abbaac97a0b3e3b5ddffe | | CR-Planner | 44.4 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Iter-RetGen | 41.6 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Search-o1 | 40.8 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Adaptive-RAG | 38 | Not recorded | 698abbaac97a0b3e3b5ddffe | | LLaDA | 36 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Selective-Context | 33.2 | Not recorded | 698abbaac97a0b3e3b5ddffe | | SuRe | 32.4 | Not recorded | 698abbaac97a0b3e3b5ddffe | | Dream | 11 | Not recorded | 698abbaac97a0b3e3b5ddffe | ### DLLM-Searcher ACC\_R: 60.4. Result ID: 699607945698665ec43efda0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"dLLMs Agent","paradigm":"P-ReAct","training":"VRPO","backbone":"SDAR","block\_size":128}. This record does not assert independent reproduction. ### R1Searcher ACC\_R: 58. Result ID: 699607945698665ec43efd9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"ARM-based LLMs Agent","setup":"modified (5.1.3)","search\_mode":"best of local/Google search"}. This record does not assert independent reproduction. ### WebSailor ACC\_R: 50.4. Result ID: 699607945698665ec43efd9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"ARM-based LLMs Agent","setup":"modified (5.1.3)","tools":"search only"}. This record does not assert independent reproduction. ### Search-R1 ACC\_R: 49.6. Result ID: 699607945698665ec43efd9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"ARM-based LLMs Agent"}. This record does not assert independent reproduction. ### IRCoT ACC\_R: 48.8. Result ID: 699607945698665ec43efd96. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### ReARTeR ACC\_R: 46.8. Result ID: 699607945698665ec43efd99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### CR-Planner ACC\_R: 44.4. Result ID: 699607945698665ec43efd98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### Iter-RetGen ACC\_R: 41.6. Result ID: 699607945698665ec43efd97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### Search-o1 ACC\_R: 40.8. Result ID: 699607945698665ec43efd9a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"ARM-based LLMs Agent"}. This record does not assert independent reproduction. ### Adaptive-RAG ACC\_R: 38. Result ID: 699607945698665ec43efd95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### LLaDA ACC\_R: 36. Result ID: 699607945698665ec43efd9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"dLLMs Agent","paradigm":"ReAct","acceleration":"Fast-dLLM"}. This record does not assert independent reproduction. ### Selective-Context ACC\_R: 33.2. Result ID: 699607945698665ec43efd94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### SuRe ACC\_R: 32.4. Result ID: 699607945698665ec43efd93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Traditional RAG"}. This record does not assert independent reproduction. ### Dream ACC\_R: 11. Result ID: 699607945698665ec43efd9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"dLLMs Agent","paradigm":"ReAct","acceleration":"Fast-dLLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.