# Long-term Dialogue Memory Management on LoCoMo Source: [Long-term Dialogue Memory Management on LoCoMo]() Collection index: [llms.txt]() Data updated: 2026-05-28T07:12:04.969Z Evaluation of model performance on the LoCoMo dataset focusing on Long-term Dialogue Memory Management, measured using generation quality metrics including F1, BLEU, ROUGE, and METEOR. 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 | Long-term Dialogue Memory Management | | Dataset (including any stated split) | LoCoMo | | Metric | 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 - [F1](): Higher is better; unit: PERCENT. - [BLEU-1](): Higher is better; unit: PERCENT. - [ROUGE-L](): Higher is better; unit: PERCENT. - [ROUGE-2](): Higher is better; unit: PERCENT. - [METEOR](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 | Result date | Report paper | | --- | --- | --- | --- | | MGRetrieval | 42.77 | Not recorded | 6a17cbe5dbd7150506f8112d | | FULL | 39.27 | Not recorded | 6a17cbe5dbd7150506f8112d | | MemoryOS | 38.48 | Not recorded | 6a17cbe5dbd7150506f8112d | | MemR3 | 35.3 | Not recorded | 6a17cbe5dbd7150506f8112d | | RAG | 34.62 | Not recorded | 6a17cbe5dbd7150506f8112d | | A-Mem | 32.43 | Not recorded | 6a17cbe5dbd7150506f8112d | | MemoryBank | 19.56 | Not recorded | 6a17cbe5dbd7150506f8112d | ### MGRetrieval F1: 42.77. Result ID: 6a17eab1fbc373592c112f51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average","pyramid layers":"4","max iterations":"4"}. This record does not assert independent reproduction. ### FULL F1: 39.27. Result ID: 6a17eab1fbc373592c112f4c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average","mode":"Complete memory as input"}. This record does not assert independent reproduction. ### MemoryOS F1: 38.48. Result ID: 6a17eab1fbc373592c112f50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average"}. This record does not assert independent reproduction. ### MemR3 F1: 35.3. Result ID: 6a17eab1fbc373592c112f4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average"}. This record does not assert independent reproduction. ### RAG F1: 34.62. Result ID: 6a17eab1fbc373592c112f4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average"}. This record does not assert independent reproduction. ### A-Mem F1: 32.43. Result ID: 6a17eab1fbc373592c112f4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average"}. This record does not assert independent reproduction. ### MemoryBank F1: 19.56. Result ID: 6a17eab1fbc373592c112f4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B and Qwen3-14B","Evaluation Protocol":"Weighted average"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.