Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• Kumiho achieves 0.565 overall F1 score on the LoCoMo benchmark (n=1,986) including 97.5% adversarial refusal accuracy.result 95%
• Kumiho achieves 93.3% judge accuracy on LoCoMo-Plus benchmark testing implicit constraint recall (n=401).result 95%
• Kumiho substantially outperforms all published baselines on LoCoMo-Plus, with the best baseline (Gemini 2.5 Pro) achieving only 45.7% accuracy.result 90%
• The architecture implements a dual-store model with Redis working memory and Neo4j long-term graph storage.technical 90%
• Kumiho's formal contribution includes proving satisfaction of the basic AGM postulates (K*2-K*6) and Hansson's belief base postulates.technical 90%
• Three architectural innovations drive Kumiho's results: prospective indexing, event extraction, and client-side LLM reranking.method 85%
• The architecture is model-decoupled, allowing switching from GPT-4o-mini to GPT-4o without pipeline changes, improving accuracy from ~88% to 93.3%.technical 85%
• The structural primitives required for cognitive memory are identical to those required for managing agent-produced work as versionable assets.technical 80%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card