Harness Continual Learning: Continual Adaptation Beyond Model Parameters
Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and routing rules. Because these contents jointly shape later execution, a harness update can disrupt previously reliable behavior even when the model is frozen. This raises a new question: how can an agent continually improve its state outside the model while retaining behavior acquired earlier? We formulate Harness Continual Learning (HCL), a new continual learning paradigm in whi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 65%What's your take on continual learning? [D] →
- PossiblePossibly related (embedding) · 62%Exploring continual learning without replay buffers: Our findings using dynamic task-similarity routing [P] →
- PossiblePossibly related (embedding) · 60%Live Continual Learning in Machine Learning [D] →
- PossiblePossibly related (embedding) · 55%Training a harness for model-agnostic and task-environment-agnostic capability improvements with PyTorch-like framework [P] →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “Harness Continual Learning: Continual Adaptation Beyond Mode” ≈ “strands-agents/harness-sdk””
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Harness Continual Learning: Continual Adaptation Beyond Mode” ≈ “aymericdamien/TopDeepLearning””