arXiv AI October 12, 2026 By Yuxin Xiao, Zhiyun Lu, Jianyu Wang, Yangtian Zhang, Yang Song, Qifan Wang, Bailin Wang

Recurrent Harness for Agentic Continual Learning

ReHarness is a recurrent harness framework designed for agentic continual learning, enabling language model agents to adapt online to distribution shifts. It augments forward read/write operations with backward revision, using feedback from each instance’s trajectory to refine the harness state. Experiments on three continual learning benchmarks and multiple language model backbones show that ReHarness outperforms baseline methods, producing source‑grounded revisions that improve stability and plasticity.

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 AI.

arXiv Machine Learning

Jul 20

Rethinking Transfer in Continual Learning: A Replay-Based Realisation

arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.

By Yang Meng, Zhenya Liu, Zhuokai Zhao, Yuxin Chen

llms efficiency

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 AI

Jun 3

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

arXiv:2606. 02461v2 Announce Type: replace Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.

By Yiheng Shu, Bernal Jim\'enez Guti\'errez, Saisri Padmaja Jonnalagedda, Yuguang Yao, Huan Sun, Yu Su

agents benchmarks

arXiv AI

Jun 2

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

arXiv:2606. 02461v1 Announce Type: new Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.

By Yiheng Shu, Bernal Jim\'enez Guti\'errez, Saisri Padmaja Jonnalagedda, Yuguang Yao, Huan Sun, Yu Su

agents benchmarks

arXiv Machine Learning

6d ago

From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning

The paper introduces Evolving Functional REpertoires (EFRE), a method that replaces a single prompt with a dynamic set of functions to enable large language models to learn new tasks sequentially without forgetting. EFRE refines existing functions when updates are compatible and creates new ones when updates conflict, thereby mitigating catastrophic forgetting and overfitting. Experiments on a three‑task continual‑learning stream show EFRE outperforms GRPO by 7.50 percentage points and reduces performance drop on a subsequent task by only 1.56 percentage points compared to base prompt optimization.

By Fengyuan Liu, Yue Wang, Hangxi Guo, Fengyuan Liu, Chenxu Wu, Yanguang Liu, Mengnan Du

llms agents reinforcement-learning

arXiv Machine Learning

Jun 5

CLaaS: Continual learning as a service for sample efficient online learning

arXiv:2606. 05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments.

By Kion Fallah, Silen Naihin, Barak Widawsky, Qingqing Mao

llms agents safety

One email a morning, machine-written

Related stories

Rethinking Transfer in Continual Learning: A Replay-Based Realisation

When Does Continual Learning Require Learning

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning

CLaaS: Continual learning as a service for sample efficient online learning