[ { "method": "Long-Context", "backbone": "GPT-5.4", "domain": "Medical", "family": "Full-context", "u": 91.4, "a": 10.4, "f": 2.3, "mgs": 80.1, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5.4", "domain": "Office", "family": "Full-context", "u": 89.6, "a": 33.9, "f": 4.5, "mgs": 56.5, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5.4", "domain": "Education", "family": "Full-context", "u": 85.6, "a": 12.8, "f": 7.8, "mgs": 68.8, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5.4", "domain": "Household", "family": "Full-context", "u": 73.4, "a": 16.8, "f": 11.4, "mgs": 54.0, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5.4", "domain": "Medical", "family": "RAG", "u": 64.8, "a": 25.0, "f": 7.9, "mgs": 44.7, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5.4", "domain": "Office", "family": "RAG", "u": 74.0, "a": 29.8, "f": 9.5, "mgs": 47.0, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5.4", "domain": "Education", "family": "RAG", "u": 32.8, "a": 12.8, "f": 32.8, "mgs": 19.2, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5.4", "domain": "Household", "family": "RAG", "u": 51.1, "a": 19.0, "f": 10.9, "mgs": 36.9, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5.4", "domain": "Medical", "family": "RAG", "u": 37.1, "a": 10.9, "f": 4.0, "mgs": 31.8, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5.4", "domain": "Office", "family": "RAG", "u": 76.0, "a": 19.9, "f": 6.3, "mgs": 57.0, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5.4", "domain": "Education", "family": "RAG", "u": 22.2, "a": 9.4, "f": 16.1, "mgs": 16.9, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5.4", "domain": "Household", "family": "RAG", "u": 39.1, "a": 14.7, "f": 14.1, "mgs": 28.7, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5.4", "domain": "Medical", "family": "External memory", "u": 65.7, "a": 24.0, "f": 6.8, "mgs": 46.6, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5.4", "domain": "Office", "family": "External memory", "u": 79.2, "a": 31.0, "f": 11.7, "mgs": 48.3, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5.4", "domain": "Education", "family": "External memory", "u": 32.2, "a": 15.0, "f": 37.2, "mgs": 17.2, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5.4", "domain": "Household", "family": "External memory", "u": 51.1, "a": 20.1, "f": 10.9, "mgs": 36.4, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5.4", "domain": "Medical", "family": "External memory", "u": 38.1, "a": 28.1, "f": 5.6, "mgs": 25.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5.4", "domain": "Office", "family": "External memory", "u": 40.3, "a": 16.4, "f": 14.4, "mgs": 28.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5.4", "domain": "Education", "family": "External memory", "u": 27.2, "a": 8.9, "f": 15.0, "mgs": 21.1, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5.4", "domain": "Household", "family": "External memory", "u": 25.5, "a": 10.3, "f": 9.2, "mgs": 20.8, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5.4", "domain": "Medical", "family": "External memory", "u": 56.7, "a": 28.6, "f": 9.0, "mgs": 36.8, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5.4", "domain": "Office", "family": "External memory", "u": 59.7, "a": 28.6, "f": 6.3, "mgs": 40.0, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5.4", "domain": "Education", "family": "External memory", "u": 16.7, "a": 13.3, "f": 33.9, "mgs": 9.5, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5.4", "domain": "Household", "family": "External memory", "u": 32.6, "a": 15.2, "f": 15.2, "mgs": 23.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5.4", "domain": "Medical", "family": "External memory", "u": 54.1, "a": 26.3, "f": 8.7, "mgs": 36.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5.4", "domain": "Office", "family": "External memory", "u": 58.6, "a": 29.6, "f": 6.9, "mgs": 38.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5.4", "domain": "Education", "family": "External memory", "u": 16.3, "a": 13.9, "f": 34.1, "mgs": 9.2, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5.4", "domain": "Household", "family": "External memory", "u": 31.6, "a": 20.1, "f": 16.8, "mgs": 21.0, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "Full-context", "u": 87.1, "a": 10.9, "f": 9.0, "mgs": 70.6, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "Full-context", "u": 90.3, "a": 19.3, "f": 6.8, "mgs": 67.9, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "Full-context", "u": 85.6, "a": 7.8, "f": 10.0, "mgs": 71.0, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "Full-context", "u": 85.3, "a": 17.9, "f": 2.2, "mgs": 68.5, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "RAG", "u": 63.8, "a": 12.5, "f": 9.0, "mgs": 50.8, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "RAG", "u": 72.7, "a": 18.7, "f": 10.8, "mgs": 52.7, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "RAG", "u": 31.1, "a": 10.6, "f": 33.9, "mgs": 18.4, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "RAG", "u": 58.2, "a": 19.0, "f": 12.0, "mgs": 41.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "RAG", "u": 37.6, "a": 7.8, "f": 9.0, "mgs": 31.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "RAG", "u": 79.9, "a": 15.8, "f": 13.1, "mgs": 58.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "RAG", "u": 23.9, "a": 5.6, "f": 22.2, "mgs": 17.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "RAG", "u": 41.3, "a": 19.6, "f": 12.5, "mgs": 29.1, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "External memory", "u": 59.5, "a": 18.2, "f": 5.6, "mgs": 45.9, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "External memory", "u": 74.0, "a": 21.1, "f": 10.4, "mgs": 52.4, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "External memory", "u": 31.7, "a": 12.8, "f": 39.4, "mgs": 16.7, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "External memory", "u": 57.1, "a": 25.0, "f": 9.2, "mgs": 38.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "External memory", "u": 40.5, "a": 16.7, "f": 9.0, "mgs": 30.7, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "External memory", "u": 40.3, "a": 17.5, "f": 20.7, "mgs": 26.3, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "External memory", "u": 28.3, "a": 8.3, "f": 38.3, "mgs": 16.0, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "External memory", "u": 19.6, "a": 15.2, "f": 15.8, "mgs": 14.0, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "External memory", "u": 50.0, "a": 14.6, "f": 10.7, "mgs": 38.1, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "External memory", "u": 68.9, "a": 21.1, "f": 11.3, "mgs": 48.2, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "External memory", "u": 20.6, "a": 13.3, "f": 34.4, "mgs": 11.7, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "External memory", "u": 44.0, "a": 15.2, "f": 10.9, "mgs": 33.3, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Deepseek-V4-Pro", "domain": "Medical", "family": "External memory", "u": 39.0, "a": 14.1, "f": 10.2, "mgs": 30.1, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Deepseek-V4-Pro", "domain": "Office", "family": "External memory", "u": 52.6, "a": 24.0, "f": 13.5, "mgs": 34.6, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Deepseek-V4-Pro", "domain": "Education", "family": "External memory", "u": 12.8, "a": 11.7, "f": 36.1, "mgs": 7.2, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Deepseek-V4-Pro", "domain": "Household", "family": "External memory", "u": 31.5, "a": 21.2, "f": 10.9, "mgs": 22.1, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "Full-context", "u": 85.2, "a": 18.2, "f": 18.6, "mgs": 56.7, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "Full-context", "u": 68.8, "a": 31.6, "f": 29.3, "mgs": 33.3, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "Full-context", "u": 76.7, "a": 13.9, "f": 29.4, "mgs": 46.6, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "Full-context", "u": 66.8, "a": 11.4, "f": 12.5, "mgs": 51.8, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "RAG", "u": 71.4, "a": 40.1, "f": 41.8, "mgs": 24.9, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "RAG", "u": 66.2, "a": 35.7, "f": 31.5, "mgs": 29.2, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "RAG", "u": 25.6, "a": 12.2, "f": 58.3, "mgs": 9.3, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "RAG", "u": 45.1, "a": 14.7, "f": 21.2, "mgs": 30.3, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "RAG", "u": 34.8, "a": 15.1, "f": 12.4, "mgs": 25.8, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "RAG", "u": 66.9, "a": 25.7, "f": 25.2, "mgs": 37.1, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "RAG", "u": 15.6, "a": 7.2, "f": 30.0, "mgs": 10.1, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "RAG", "u": 33.2, "a": 11.4, "f": 17.4, "mgs": 24.3, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "External memory", "u": 71.9, "a": 44.3, "f": 41.2, "mgs": 23.5, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "External memory", "u": 63.0, "a": 36.8, "f": 37.8, "mgs": 24.7, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "External memory", "u": 26.7, "a": 13.3, "f": 58.3, "mgs": 9.6, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "External memory", "u": 46.2, "a": 13.6, "f": 18.5, "mgs": 32.5, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "External memory", "u": 53.3, "a": 53.6, "f": 54.8, "mgs": 11.2, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "External memory", "u": 43.5, "a": 29.8, "f": 35.1, "mgs": 19.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "External memory", "u": 17.2, "a": 48.3, "f": 17.2, "mgs": 8.6, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "External memory", "u": 33.7, "a": 23.3, "f": 17.1, "mgs": 21.4, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "External memory", "u": 62.4, "a": 44.8, "f": 41.8, "mgs": 20.0, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "External memory", "u": 65.6, "a": 34.5, "f": 34.7, "mgs": 28.1, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "External memory", "u": 16.1, "a": 16.1, "f": 56.7, "mgs": 5.9, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "External memory", "u": 41.2, "a": 20.0, "f": 31.7, "mgs": 22.5, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Llama-4-Maverick", "domain": "Medical", "family": "External memory", "u": 53.3, "a": 42.2, "f": 39.5, "mgs": 18.6, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Llama-4-Maverick", "domain": "Office", "family": "External memory", "u": 45.5, "a": 32.2, "f": 31.5, "mgs": 21.1, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Llama-4-Maverick", "domain": "Education", "family": "External memory", "u": 12.2, "a": 12.7, "f": 50.6, "mgs": 5.3, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Llama-4-Maverick", "domain": "Household", "family": "External memory", "u": 36.8, "a": 19.3, "f": 29.6, "mgs": 20.9, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5-mini", "domain": "Medical", "family": "Full-context", "u": 85.7, "a": 19.8, "f": 20.3, "mgs": 54.8, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5-mini", "domain": "Office", "family": "Full-context", "u": 89.6, "a": 32.2, "f": 3.2, "mgs": 58.9, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5-mini", "domain": "Education", "family": "Full-context", "u": 80.6, "a": 15.6, "f": 11.1, "mgs": 60.5, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-5-mini", "domain": "Household", "family": "Full-context", "u": 76.6, "a": 24.5, "f": 14.7, "mgs": 49.4, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5-mini", "domain": "Medical", "family": "RAG", "u": 57.1, "a": 36.5, "f": 18.6, "mgs": 29.5, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5-mini", "domain": "Office", "family": "RAG", "u": 74.7, "a": 31.0, "f": 7.7, "mgs": 47.6, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5-mini", "domain": "Education", "family": "RAG", "u": 30.6, "a": 19.4, "f": 27.2, "mgs": 17.9, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-5-mini", "domain": "Household", "family": "RAG", "u": 48.9, "a": 23.4, "f": 10.3, "mgs": 33.6, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5-mini", "domain": "Medical", "family": "RAG", "u": 37.6, "a": 24.5, "f": 6.8, "mgs": 26.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5-mini", "domain": "Office", "family": "RAG", "u": 75.3, "a": 24.6, "f": 5.4, "mgs": 53.8, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5-mini", "domain": "Education", "family": "RAG", "u": 24.4, "a": 10.6, "f": 22.8, "mgs": 16.9, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-5-mini", "domain": "Household", "family": "RAG", "u": 37.0, "a": 19.6, "f": 6.0, "mgs": 27.9, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5-mini", "domain": "Medical", "family": "External memory", "u": 58.6, "a": 40.6, "f": 21.5, "mgs": 27.3, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5-mini", "domain": "Office", "family": "External memory", "u": 71.4, "a": 35.7, "f": 10.4, "mgs": 41.2, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5-mini", "domain": "Education", "family": "External memory", "u": 30.6, "a": 18.3, "f": 31.1, "mgs": 17.2, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-5-mini", "domain": "Household", "family": "External memory", "u": 47.3, "a": 25.5, "f": 10.3, "mgs": 31.6, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5-mini", "domain": "Medical", "family": "External memory", "u": 40.0, "a": 38.5, "f": 27.7, "mgs": 17.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5-mini", "domain": "Office", "family": "External memory", "u": 58.4, "a": 33.3, "f": 9.5, "mgs": 35.3, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5-mini", "domain": "Education", "family": "External memory", "u": 39.4, "a": 12.8, "f": 34.4, "mgs": 22.6, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-5-mini", "domain": "Household", "family": "External memory", "u": 37.5, "a": 24.5, "f": 22.8, "mgs": 21.9, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5-mini", "domain": "Medical", "family": "External memory", "u": 48.6, "a": 43.2, "f": 37.9, "mgs": 17.1, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5-mini", "domain": "Office", "family": "External memory", "u": 71.4, "a": 33.9, "f": 8.6, "mgs": 43.2, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5-mini", "domain": "Education", "family": "External memory", "u": 21.7, "a": 13.3, "f": 41.7, "mgs": 11.0, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-5-mini", "domain": "Household", "family": "External memory", "u": 41.8, "a": 21.2, "f": 21.2, "mgs": 26.0, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5-mini", "domain": "Medical", "family": "External memory", "u": 48.0, "a": 45.2, "f": 39.5, "mgs": 15.9, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5-mini", "domain": "Office", "family": "External memory", "u": 71.6, "a": 34.0, "f": 9.1, "mgs": 43.0, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5-mini", "domain": "Education", "family": "External memory", "u": 20.5, "a": 12.2, "f": 44.0, "mgs": 10.1, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-5-mini", "domain": "Household", "family": "External memory", "u": 40.2, "a": 24.4, "f": 19.6, "mgs": 24.4, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "Full-context", "u": 64.8, "a": 24.0, "f": 7.3, "mgs": 45.6, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-4o-mini", "domain": "Office", "family": "Full-context", "u": 38.3, "a": 41.5, "f": 10.4, "mgs": 20.1, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-4o-mini", "domain": "Education", "family": "Full-context", "u": 36.1, "a": 26.1, "f": 13.3, "mgs": 23.1, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "GPT-4o-mini", "domain": "Household", "family": "Full-context", "u": 35.3, "a": 9.8, "f": 6.0, "mgs": 30.0, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "RAG", "u": 46.7, "a": 58.9, "f": 24.9, "mgs": 14.4, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-4o-mini", "domain": "Office", "family": "RAG", "u": 30.5, "a": 62.0, "f": 28.8, "mgs": 8.3, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-4o-mini", "domain": "Education", "family": "RAG", "u": 10.6, "a": 27.8, "f": 30.0, "mgs": 5.3, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "GPT-4o-mini", "domain": "Household", "family": "RAG", "u": 16.3, "a": 18.5, "f": 19.6, "mgs": 10.7, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "RAG", "u": 28.1, "a": 17.2, "f": 7.3, "mgs": 21.6, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-4o-mini", "domain": "Office", "family": "RAG", "u": 32.5, "a": 31.0, "f": 22.5, "mgs": 17.4, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-4o-mini", "domain": "Education", "family": "RAG", "u": 6.1, "a": 16.7, "f": 11.7, "mgs": 4.5, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "GPT-4o-mini", "domain": "Household", "family": "RAG", "u": 18.5, "a": 16.3, "f": 14.1, "mgs": 13.3, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "External memory", "u": 50.0, "a": 57.8, "f": 22.0, "mgs": 16.4, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-4o-mini", "domain": "Office", "family": "External memory", "u": 39.6, "a": 66.1, "f": 29.7, "mgs": 9.4, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-4o-mini", "domain": "Education", "family": "External memory", "u": 10.0, "a": 28.9, "f": 30.6, "mgs": 4.9, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "GPT-4o-mini", "domain": "Household", "family": "External memory", "u": 17.4, "a": 18.5, "f": 20.1, "mgs": 11.3, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "External memory", "u": 34.3, "a": 67.2, "f": 28.2, "mgs": 8.1, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-4o-mini", "domain": "Office", "family": "External memory", "u": 34.4, "a": 63.7, "f": 21.2, "mgs": 9.8, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-4o-mini", "domain": "Education", "family": "External memory", "u": 2.8, "a": 31.1, "f": 17.8, "mgs": 1.6, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "GPT-4o-mini", "domain": "Household", "family": "External memory", "u": 38.6, "a": 21.7, "f": 9.2, "mgs": 27.4, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "External memory", "u": 36.7, "a": 55.7, "f": 29.4, "mgs": 11.5, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-4o-mini", "domain": "Office", "family": "External memory", "u": 20.8, "a": 54.4, "f": 24.8, "mgs": 7.1, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-4o-mini", "domain": "Education", "family": "External memory", "u": 3.3, "a": 28.3, "f": 29.4, "mgs": 1.7, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "GPT-4o-mini", "domain": "Household", "family": "External memory", "u": 8.7, "a": 22.3, "f": 19.0, "mgs": 5.5, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-4o-mini", "domain": "Medical", "family": "External memory", "u": 35.2, "a": 57.8, "f": 29.9, "mgs": 10.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-4o-mini", "domain": "Office", "family": "External memory", "u": 20.1, "a": 53.9, "f": 25.6, "mgs": 6.9, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-4o-mini", "domain": "Education", "family": "External memory", "u": 3.3, "a": 27.2, "f": 31.7, "mgs": 1.7, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "GPT-4o-mini", "domain": "Household", "family": "External memory", "u": 7.1, "a": 25.5, "f": 17.4, "mgs": 4.3, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "Full-context", "u": 84.8, "a": 27.1, "f": 26.0, "mgs": 45.7, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "Full-context", "u": 88.3, "a": 69.0, "f": 64.9, "mgs": 9.6, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "Full-context", "u": 93.9, "a": 32.8, "f": 64.4, "mgs": 22.4, "source": "paper", "verified": true }, { "method": "Long-Context", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "Full-context", "u": 65.8, "a": 29.3, "f": 36.4, "mgs": 29.5, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "RAG", "u": 75.2, "a": 59.9, "f": 64.4, "mgs": 10.7, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "RAG", "u": 72.8, "a": 67.3, "f": 61.3, "mgs": 9.1, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "RAG", "u": 39.4, "a": 33.3, "f": 65.0, "mgs": 9.2, "source": "paper", "verified": true }, { "method": "RAG-Naive", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "RAG", "u": 46.2, "a": 37.0, "f": 60.3, "mgs": 11.6, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "RAG", "u": 37.6, "a": 18.8, "f": 16.9, "mgs": 25.4, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "RAG", "u": 69.5, "a": 44.4, "f": 55.4, "mgs": 17.2, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "RAG", "u": 21.1, "a": 15.0, "f": 40.6, "mgs": 10.7, "source": "paper", "verified": true }, { "method": "RAG-Policy", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "RAG", "u": 34.2, "a": 30.4, "f": 53.3, "mgs": 11.1, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "External memory", "u": 74.3, "a": 48.4, "f": 63.8, "mgs": 13.8, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "External memory", "u": 70.8, "a": 66.7, "f": 61.7, "mgs": 9.0, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "External memory", "u": 39.4, "a": 38.3, "f": 69.4, "mgs": 7.4, "source": "paper", "verified": true }, { "method": "A-Mem", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "External memory", "u": 47.8, "a": 34.8, "f": 59.2, "mgs": 12.7, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "External memory", "u": 41.4, "a": 48.4, "f": 50.9, "mgs": 10.5, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "External memory", "u": 43.5, "a": 62.0, "f": 38.3, "mgs": 10.2, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "External memory", "u": 31.1, "a": 31.7, "f": 45.6, "mgs": 11.6, "source": "paper", "verified": true }, { "method": "Mem0", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "External memory", "u": 19.0, "a": 21.8, "f": 27.2, "mgs": 10.8, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "External memory", "u": 57.8, "a": 51.8, "f": 63.2, "mgs": 10.3, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "External memory", "u": 71.4, "a": 62.0, "f": 57.2, "mgs": 11.6, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "External memory", "u": 25.2, "a": 29.8, "f": 57.8, "mgs": 7.5, "source": "paper", "verified": true }, { "method": "ReMem-I", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "External memory", "u": 34.6, "a": 25.4, "f": 46.8, "mgs": 13.7, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Medical", "family": "External memory", "u": 56.3, "a": 53.9, "f": 63.7, "mgs": 9.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Office", "family": "External memory", "u": 70.7, "a": 61.5, "f": 58.0, "mgs": 11.4, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Education", "family": "External memory", "u": 22.7, "a": 24.8, "f": 55.3, "mgs": 7.6, "source": "paper", "verified": true }, { "method": "ReMem-S", "backbone": "Gemini-2.5-Flash-Lite", "domain": "Household", "family": "External memory", "u": 33.0, "a": 28.6, "f": 45.2, "mgs": 12.9, "source": "paper", "verified": true } ]