paperEmergent Mind·25 Oct 20264.6
Tests whether self-evolving agents like ReasoningBank, GEPA and Meta-Harness learn new tasks without forgetting old ones.
paperHugging Face Daily Papers·21 Oct 20263.5
Memory-centric continual learning for AI agents.
paperarXiv (systems, data, ML)·22 Oct 20263.4
Writes continual updates forward-only into an LM native n-gram memory table.
paperHugging Face Daily Papers·21 Oct 20263.4
Recursive self-improvement for forecasting in open worlds.
paperarXiv (systems, data, ML)·22 Oct 20263.3
Harness-evolving recursive distillation for continual learning.