Harness Continual Learning: Continual Adaptation Beyond Model Parameters

arXiv:2608.19013 · cs.LG, cs.AI · Submitted 2026-08-19 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-08-19

Updated: 2026-09-30

Project page: https://boringkey.github.io/Harness-Continual-Learning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Continual Learning — 1× in this paper · explained in 2 episodes

Sources

• CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
• MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks