arXiv:2605. 05097v3 Announce Type: replace Abstract: LLMs are trained once, then deployed into a world that never stops changing.
arXiv:2608.22215v1 Announce Type: new Abstract: Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat externa...
arXiv:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...
arXiv:2610.08718v1 Announce Type: cross Abstract: Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgettin...
arXiv:2609.16053v1 Announce Type: cross Abstract: Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new inf...
arXiv:2607. 26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?
arXiv:2608. 19514v1 Announce Type: cross Abstract: Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems.
We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre? sents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns through local updates without end-to-end backpropagation through its feature-generating system.
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2512. 03627v2 Announce Type: replace Abstract: Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember.
The paper introduces Hippocam, a hierarchical memory and continual learning architecture for large language model agents that mirrors human memory processes. Hippocam organizes an agent’s work into nested intents, keeping the current intent active while consolidating completed intents into task‑relevant outcomes and states, and recursively abstracts earlier history to reduce detail over time. When recalled, past experiences are re‑integrated and further consolidated with new data, reinforcing and updating knowledge without requiring parameter updates.
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 foundation model frozen. HCL defines harness-level forgetting and proposes guarded harness evolution with a Continual Optimizer and Evaluator to balance improvement, retention, and validity. Experiments across textual reasoning, multimodal perception, and open‑world interaction show over 10% performance gains and demonstrate explicit control over the stability–plasticity trade‑off.
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.