MIRIX-2.0 Multi-Agent Memory System Released
The story so far
qwen released MIRIX-2.0, a multi-agent memory system that requires no fine-tuning. MIRIX-2.0 achieved 91.4% accuracy on LoCoMo without fine-tuning, outperformed the strongest baseline by 14.3 points on LongMemEval-S, and surpassed HyperMem by 53.0 and 42.0 points on single-hop and multi-hop document question answering, respectively. The system is designed for LLM agents to achieve high precision and efficiency, suitable for question answering and procedural benchmark tests.
AI-written from the reports · Updated 9 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersMIRIX-2.0: A multi-agent memory system that requires no fine-tuning
MIRIX-2.0 achieves 91.4% accuracy on LoCoMo without fine-tuning, leads the strongest baseline by 14.3 points on LongMemEval-S, and surpasses HyperMem by 53.0 and 42.0 points on single-hop and multi-hop document question answering.
Heat over time
- Now
- 5
- Peak
- 617 Nov, 01:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.