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.
arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.
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?
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.
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.
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.
arXiv:2606. 05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments.
arXiv:2606. 01379v1 Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored.
The paper introduces Harness Continual Learning (HCL), a paradigm where an agent’s state evolves through prompts, memories, tools, skills, and routing rules while keeping the underlying foundation model frozen. HCL defines harness-level forgetting and proposes a guarded evolution process involving a Continual Optimizer and Evaluator to ensure improvements without losing prior behavior. Experiments across textual reasoning, multimodal perception, and open‑world interaction show over 10% performance gains and demonstrate how the stability–plasticity trade‑off can be explicitly tuned.
arXiv:2507. 14725v4 Announce Type: replace-cross Abstract: Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences.
arXiv:2609.36626v1 Announce Type: new Abstract: Language-model agents increasingly rely on persistent natural-language skills to adapt beyond their frozen model parameters. When a shared skill is rep...
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.
MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.