Recursa: Toward Recursively Self-Improving Foundation Model Systems
Recursa uses domain maps, reusable skills, memory, and multi-agent validation to help foundation model systems improve from their own task experience.
ls ./papers | grep "#agent memory"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
2 papers · #agent memory
Recursa uses domain maps, reusable skills, memory, and multi-agent validation to help foundation model systems improve from their own task experience.
HABIT-Bench evaluates AI agents' ability to infer user habits from sparse, longitudinal evidence and apply them contextually, revealing key challenges in memory-based personalization.