arXiv Machine Learning October 23, 2026 By Xun Sun, Thanh Thi Nguyen, Thuy-Trang Vu

HERD: Harness-Evolving Recursive Distillation for Continual Learning

Read the original on arXiv Machine Learning →

HERD (Harness-Evolving Recursive Distillation) is a hybrid continual learning framework that combines harness-based non‑parametric methods with parametric distillation. It refines reusable skills in a harness while storing high‑residual examples in bounded memory, and applies drift‑constrained distillation with dual anchors to reduce forgetting. On the 25‑stage TRACE+17 task stream, HERD matches the best parametric baseline in new‑task learning while achieving the lowest forgetting and strongest retention of general capabilities under fixed memory and compute budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 10

When Does Continual Learning Require Learning

arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?

By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai

llms agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 16

CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework

arXiv:2609.17026v1 Announce Type: new Abstract: Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a da...

By Yunxiang Fu, Meng Lou, Zicheng Liao, Yizhou Yu

fine-tuning efficiency benchmarks

arXiv AI

Aug 13

Representation Finetuning for Continual Learning

arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.

By Haihua Luo, Xuming Ran, Tommi K\"arkk\"ainen, Huiyan Xue, Zhonghua Chen, Qi Xu, Fengyu Cong

fine-tuning benchmarks

arXiv Machine Learning

Sep 15

Realistic Continual Learning Approach using Pre-trained Models

arXiv:2404.07729v2 Announce Type: replace Abstract: Continual learning (CL) evaluates adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forg...

By Nadia Nasri, Carlos Guti\'errez-\'Alvarez, Sergio Lafuente-Arroyo, Saturnino Maldonado-Basc\'on, Roberto J. L\'opez-Sastre

benchmarks

arXiv Machine Learning

Oct 2

ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning

arXiv:2609.38833v1 Announce Type: new Abstract: Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting...

By Sungmin Kang, Zhengzhong Tu, Sunwoo Lee

arXiv Machine Learning

Jul 3

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

arXiv:2607. 01763v1 Announce Type: new Abstract: Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities.

By Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu

reinforcement-learning efficiency

One email a morning, machine-written

Related stories

When Does Continual Learning Require Learning

CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework

Representation Finetuning for Continual Learning

Realistic Continual Learning Approach using Pre-trained Models

ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training