# Question Answering on LoCoMo excluding adversarial (test) Source: [Question Answering on LoCoMo excluding adversarial (test)]() Collection index: [llms.txt]() Data updated: 2026-05-04T08:45:08.039Z Evaluation of model performance on the LoCoMo dataset, specifically excluding adversarial examples and evaluated on the test split, focusing on F1 metrics broken down by question complexity (single-hop, multi-hop, temporal, open-domain). 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 | Question Answering | | Dataset (including any stated split) | LoCoMo excluding adversarial (test) | | Metric | Overall F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Overall F1](): Higher is better; unit: PERCENT. - [Single-hop F1](): Higher is better; unit: PERCENT. - [Multi-hop F1](): Higher is better; unit: PERCENT. - [Temporal F1](): Higher is better; unit: PERCENT. - [Open-domain F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall F1 | Result date | Report paper | | --- | --- | --- | --- | | MemRouter | 55.5 | Not recorded | 69f82813c0f56ed843088a95 | | MemRouter | 52 | Not recorded | 69f82813c0f56ed843088a95 | | Memory-R1-GRPO | 43.1 | Not recorded | 69f82813c0f56ed843088a95 | | MemoryOS | 34.6 | Not recorded | 69f82813c0f56ed843088a95 | | Mem0 | 30.6 | Not recorded | 69f82813c0f56ed843088a95 | | A-Mem | 26.1 | Not recorded | 69f82813c0f56ed843088a95 | | LoCoMo (RAG) | 9 | Not recorded | 69f82813c0f56ed843088a95 | ### MemRouter Overall F1: 55.5. Result ID: 69f85c7947f34ce924dc2695. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen3.5-35B-A3B","Backbone Transfer Setting":"same router, no router retraining","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### MemRouter Overall F1: 52. Result ID: 69f85c7947f34ce924dc2694. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### Memory-R1-GRPO Overall F1: 43.1. Result ID: 69f85c7947f34ce924dc2693. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### MemoryOS Overall F1: 34.6. Result ID: 69f85c7947f34ce924dc2692. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### Mem0 Overall F1: 30.6. Result ID: 69f85c7947f34ce924dc2691. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### A-Mem Overall F1: 26.1. Result ID: 69f85c7947f34ce924dc2690. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. ### LoCoMo (RAG) Overall F1: 9. Result ID: 69f85c7947f34ce924dc268f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Answer Agent / Backbone":"Qwen2.5-7B-Instruct","Retrieval and Prompting Pipeline":"Own system-level"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.