lifelong-learning

LiSA (Lifelong Safety Adaptation) is a framework that enhances AI agent safety guardrails by converting occasional failures into reusable policy abstractions and using evidence-aware confidence gating to perform well under sparse and noisy feedback, addressing the critical need for adaptive safety in real-world deployments.

Preprint SEAL outlines how future language models could self-update post-deployment, hinting GPT-6 might exhibit computational life via evolving internal states.

CobwebTM is a low-parameter lifelong hierarchical topic modeling approach that adapts the Cobweb algorithm to continuous document embeddings, enabling unsupervised topic discovery and dynamic hierarchical organization without predefining topic counts. The method combines incremental symbolic concept formation with pretrained representations to achieve strong topic coherence while avoiding catastrophic forgetting.

SkillFlow introduces a benchmark of 166 tasks across 20 families for evaluating autonomous agents' ability to discover, repair, and maintain skills over time through a lifelong learning protocol. Experiments reveal a substantial capability gap among leading models, with Claude Opus 4.6 improving significantly while others show limited or negative gains from skill evolution.