Online Continual Learning

Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints. Existing methods rely either on replay buffers that exploit latent space structure, or on regularization alone. We present CLIMB (Continual Learning with Intelligent Memory Bank), which combines both simultaneously. Our method introduces a hierarchical centroid-based memory, bounded in total number of stored images, combined with knowledge distillation on replayed examples to limit representation drift. The memory groups similar images into centroids, providing hard-to-discriminate examples for contrastive learning while covering the diversity of observed distributions. Experiments on Split CIFAR-100 and Split ImageNet-100, on standard benchmarks from the state-of-the-art as well as a new protocol with irregular task distributions show that CLIMB outperforms state-of-the-art OCSSL methods.

Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a principled theoretical foundation in CL for understanding attack and defense remains lacking. In this paper, we develop a theoretical framework to analyze strategic attacks and defenses in regularization-based CL, a cornerstone of recent CL theory. By framing the adversary-defender interaction as an online zero-sum game, we first establish a fundamental performance limit: no defense succeeds when an adversary poisons a linear proportion of tasks by injecting unbounded noise or pattern shifts in regularization-based CL. We then analyze two possibly defensible scenarios: infrequent attacks and bounded noise per attack. For the former regime, we propose a task-to-task verification mechanism to detect data poisoning and reduce cumulative bias for learning convergence. For the latter regime, we derive a robust defense that minimizes the model's sensitivity to poisoned features, provably accelerating the convergence rate. Extensive experiments on realistic tasks further validate our theoretical results.

Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally. We give a provable account on recurring-regime streams. Given segmentation, a warm-start library learner attains amortized recovery cost $O\!\big(KD/\varepsilon^2+(R-K)\logK/Δ^2\big)$ versus a memoryless re-estimator's $Θ(RD/\varepsilon^2)$, an advantage $(R-K)\,Θ(D/\varepsilon^2)$ growing with dimension $D$ and recurrence density. The mechanism is a decoupling: recognizing which of $K$ seen regimes is active costs $O(\log K/Δ^2)$, independent of $D$, whereas estimating a regime costs $Θ(D/\varepsilon^2)$. We prove this is tight: matching lower bounds give recognition $Θ(\log K/Δ^2)$ and a memoryless-class bound $Ω(RD/\varepsilon^2)$, so each term is individually minimax-tight (the joint statement is conditional). The separation is born-immune (a memoryless learner's advantage is identically zero) and paradigm-level: it matches, and does not beat, a fair spawn-capable Bayesian baseline; the contribution is attaining this cost structure without end-to-end backprop and with zero forgetting by construction. A count-calibrated variant ties the baseline's leading constant up to a bounded, never-negative per-recurrence overshoot, hyperparameter-free and with no per-step transcendentals. We bound the scope: recognizable regimes are capped by simplex packing (walls $e^{Θ(D)}$); autonomous segmentation is impossible at the packing wall (no detector escapes the false-alarm/delay frontier as regimes overlap); the advantage vanishes under overlap. The dimension-dependent separation is corroborated on synthetic streams and real $k$-mer genome distributions (memoryless cost $\propto D^{1.04}$, recognition $D$-independent); the one real sequential stream sits in the $D{=}1$ near-null corner.

Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process. We investigate whether models can instead learn online from this experience, converting transient computation (reasoning traces) into persistent reusable knowledge, and without external supervision or access to future data. We show that In-Context Learning (ICL) over raw reasoning traces fails to generalize, reflecting a fundamental limitation of token-level reuse: individual traces lack the abstraction needed for transfer, even after refinement (e.g. self-reflection). In contrast, drawing inspiration from recent works on unsupervised reinforcement learning, we find that lightweight per-instance training with self-generated test-time signals (majority voting) as rewards yields substantial gains, often surpassing full-dataset offline training, motivating a shift from raw traces to learned latent representations. Building on this insight, we propose an online method that distills inference-time compute spent on encountered problems into compact modular latent memories capturing the underlying reasoning structure. These memories are stored and retrieved for future inputs, enabling continual improvement while avoiding catastrophic forgetting through modular design. Importantly, our method is highly efficient, parametrized as extremely lightweight soft prompt memories (~0.001% of model parameters) and trained with only a few gradient steps, yet achieving performance competitive with full parametric updates and offline training. Across challenging mathematical reasoning benchmarks, our approach significantly outperforms zero-shot and raw data ICL baselines, while transferring effectively across datasets.

Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under strict single-pass constraints and without any explicit task identifiers. Existing online TFCL paradigms primarily rely on parameter-efficient prompt tuning or dynamic structure expansion driven by training-coupled optimization dynamics, such as empirical loss fluctuations or evolving latent distances. As a result, these training-coupled solvers remain agnostic to the structural origins of distribution drift, mechanically enforcing a fixed strategy across fundamentally distinct streaming variations. To address this gap, we propose LargeMonitor, a framework that leverages large pretrained foundation models to autonomously orchestrate task-free continuous adaptation. Specifically, LargeMonitor introduces a decoupled detection module utilizing the frozen, stable representation space of large vision models (LVMs) to achieve robust, zero-shot drift detection without training-dependent interference or brittle threshold tuning. Upon a confirmed drift, the framework activates a context-aware diagnostic module driven by large multimodal models (LMMs) to interpret the precise semantic etiologies of the stream variation (e.g., novel class emergence vs. environmental domain shift). This dual-stage capability empowers the continuous learner to dynamically deploy adaptive and shift-specific optimization strategies. Extensive experiments across multiple TFCL settings and benchmarks demonstrate that LargeMonitor achieves precise, robust detection and diagnosis of complex data streams while consistently improving the performance of existing online TFCL algorithms.

Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems genuinely improve with experience. CL-Bench spans six diverse domains (software engineering, signal processing, disease outbreak forecasting, database querying, strategic game-playing, and demand forecasting), each validated by domain experts and designed so that tasks share a learnable latent structure (codebase layout, disease outbreak dynamics, opponent strategies) that a stateful system can discover online but a stateless one cannot. We evaluate frontier models across several agent architectures, from naive in-context learning (ICL) to dedicated memory systems, introducing a gain metric to isolate learning from prior capabilities. We find that these systems leave headroom for improved continual learning: agents frequently overfit to immediate observations or fail to reuse knowledge across instances, and dedicated memory systems do not fix this -- in fact, naive ICL outperforms systems dedicated to memory management. CL-Bench is the first benchmark to evaluate continual learning across diverse real-world domains with expert-validated tasks and isolate online learning from underlying model capability, showing a need for better continual learning systems.

Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks. However, agent actions and environmental transitions can only be sampled once per scenario, as real-world environments cannot be trivially reset. To this end, we investigate an experiential and online continual learning setting in which agents learn from a stream of scenarios. We propose continual learning as-a-service (CLaaS), a system which enables agents to improve during deployment, abstracted behind a chat API. To increase sample efficiency, CLaaS stores rollouts in an experience replay buffer for gradient reuse during asynchronous training. We evaluate CLaaS on an adversarial task, demonstrating that parametric updates lead to superior forward transfer and less forgetting than in-context learning, with replay being a critical choice for sample efficiency.

Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive sequentially and must be processed in a single pass without simultaneously revisiting past observations. Standard architectures, including recurrent neural networks and transformers, are constrained by either truncated backpropagation through time horizon or explicit input window length for long range credit assignment. To address these limitations, we propose SHARP (Sleep-based Hierarchical Accelerated Replay), a framework that decomposes temporal learning into two complementary components: a memory module that accumulates a structured history of past inputs, and a pattern-recognition module that operates over this memory. This separation enables resource- and compute-efficient adaptation to non-stationary dynamics by eliminating the need for backpropagation through time across many steps for long-range credit assignment. Inspired by the accelerated replay observed in rodents during slow-wave sleep, SHARP incorporates offline (sleep) phases in which temporally structured memory traces are replayed in an accelerated form and integrated into higher-level memory representations, improving long-range context retention. Through controlled simulations and ablation studies, we characterize the key properties of the proposed framework. In benchmark datasets such as text8 and PG-19, we demonstrate that SHARP improves over recurrent baselines by retaining next-token predictive performance on previously seen data while continuing to learn from the current stream and generalizing to future unseen data. These gains are enabled by its hierarchical structure, which yields an exponentially increasing effective temporal context with only linear-time computational cost.

Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustains informative uncertainty. This non-degenerate posterior enables fully online, buffer-free active querying via Monte Carlo disagreement, reducing label queries and backpropagation updates under imbalance. BiMU sustains learning and strong OOD detection on 1000-tasks Permuted-MNIST, and on OpenLORIS-Object achieves up to 32$\times$ label/update savings at matched accuracy under class imbalance and feature compression.

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where training is multiple epoch dependent on large datasets. The main challenge faced by OCL is to overcome catastrophic forgetting of past tasks (stability) while learning new ones efficiently (plasticity). Existing methods counter forgetting via replay-based rehearsal, output level distillation, fixed regularization, or meta-learning on the current data. However, these methods have limitations: rehearsal introduces a stored sample bias; distillation operates on output-distributions without modulating parameter updates; fixed-regularization penalizes parameters irrespective of sensitivity; stream-only meta-learning lacks a feedback controlled parameter update. We propose Meta-Adaptive Network Gradient Optimization (MANGO), an OCL framework that balances stability-plasticity via gradient-gating and meta-learned regularization. Gradient-gating scales parameter updates based on sensitivity, preventing destructive updates. Meta-learned regularization adapts stability coefficients, evaluating the effect of parameter update on replay. In MANGO, replay acts as both a training signal and a forgetting evaluator. We evaluated our method on three standard OCL benchmark datasets. MANGO outperforms strong baselines, achieving state-of-the-art results with consistent performance across replay sizes. In domain incremental learning on CLEAR-10 and class incremental learning on CIFAR-100 and Tiny-ImageNet, it achieves highest accuracy among all baselines and achieves positive Backward Transfer, overcoming forgetting on CLEAR-10.

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both horizontally (sibling classes) and vertically (coarse or fine categories). To better reflect this context, we introduce a new problem setting, DHOCL (Online Continual Learning from Dynamic Hierarchies), where taxonomies evolve across granularities and each sample provides supervision at a single hierarchical level. In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency, and (ii) the dynamically evolving hierarchies induce granularity-dependent interference, destabilizing popular replay and regularization mechanisms and thereby exacerbating catastrophic forgetting. To tackle these issues, we propose HALO (Hierarchical Adaptive Learning with Organized Prototypes), which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves. Extensive experiments on multiple benchmarks demonstrate that HALO consistently outperforms existing methods across hierarchical accuracy, mistake severity, and continual performance.

Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite these, they still fail in online class-incremental learning due to two coupled miscalibrations: (i) their split criterion grows unreliable as the class count K expands, and (ii) the absence of knowledge transfer at split time. Both failures share a common root: the range of Information Gain intrinsically scales with log2 K. Consequently, any Hoeffding-style confidence radius derived from it must inevitably grow with the class count, making a K-independent split criterion structurally impossible, taking away the potential benefits of applying streaming decision trees to continual learning. To fix this issue, we present MIST (McDiarmid Incremental Streaming Tree), which resolves both failures through three integrated components: (i) a tight, K-independent McDiarmid confidence radius for Gini splitting that acts as a structural regulariser; (ii) a Bayesian inheritance protocol that projects parent statistics to child nodes via truncated-Gaussian moments, with variance reduction guarantees strongest precisely when splitting is most conservative; and (iii) per-leaf KLL quantile sketches that support both continuous threshold evaluation and geometry-adaptive leaf prediction from a single data structure. On standard and stress-test tabular streams, MIST is competitive with global parametric methods on near-Gaussian benchmarks and uniquely robust on non-Gaussian geometry where SOTA benchmarks collapse.

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a mechanism for forgetting, can serve this role by gradually discarding information stored in the weights. However, a fixed scalar weight decay drives this forgetting uniformly over time and uniformly across all parameters, even when some encode stable knowledge while others track rapidly changing targets. We introduce Forgetting through Adaptive Decay (FADE), which adapts per-parameter weight decay rates online via approximate meta-gradient descent. We derive FADE for the online linear setting and apply it to the final layer of neural networks. Our empirical analysis shows that FADE automatically discovers distinct decay rates for different parameters, complements step-size adaptation, and consistently improves over fixed weight decay across online tracking and streaming classification problems.

In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inception, must be overcome. The evaluation of continual learning methods relies on splitting a known homogeneous dataset and learning the associated tasks one after the other. We argue that most CL methods introduce a priori information about the data to come and cannot be considered agnostic. We exemplify this point with the case of methods relying on pretrained feature extractors, which are still used in CL. After showing that pretrained feature extractors imply a loss of generality with respect to the data that can be learned by the model, we then discuss other kinds of a priori information introduced in other CL methods. We then present the Online Patch Redundancy Eliminator (OPRE), an online dataset-compression algorithm that discards information through two explicit, input-space criteria. With a classifier that was randomly initialized at test time, OPRE's performance matches reported state-of-the-art online continual-learning methods on CIFAR 10 and CIFAR-100 without any pretrained feature extractor, and outperforms GDumb at an identical memory budget-while making only minimal and interpretable assumptions about the data to come. We frame these results as an empirical, information-theoretic perspective on continual learning.

Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving past knowledge to prevent catastrophic forgetting. Nowadays, with the flourish of large pre-trained models (LPMs), efficiency has become increasingly critical for CL, due to their substantial computational demands and growing parameter sizes. In this paper, we introduce TreeLoRA (K-D Tree of Low-Rank Adapters), a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity to enable efficient CL, particularly for LPMs. To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds to efficiently explore the task structure. Furthermore, we use sparse gradient updates to facilitate parameter optimization, making the approach better suited for LPMs. Theoretical analysis is provided to justify the rationale behind our approach, and experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach across various domains, including vision and natural language processing tasks.

Continual learning (CL) agents incrementally learn from sequentially arriving data and adapt to the dynamic, ever-changing nature of real-world environments. However, many existing CL methods suffer performance degradation in evolving, imbalanced data streams due to limited adaptation to changing class frequencies or ineffective use of mixed data from new and previously observed classes. To deal with these challenges, we propose an analytic imbalance rectifier (AIR) algorithm for real-world CL. AIR is an online exemplar-free approach with a frozen backbone as the feature extractor and a closed-form incremental classifier whose weight equals the joint-learning weight for the same class-weighted ridge objective. AIR addresses class imbalance with an analytic reweighting module (ARM) that calculates a reweighting factor for each class in the loss function to equalize total sample weights across classes. Under long-tailed class-incremental learning, AIR leads 28 baselines in aggregate accuracy and exemplar-free methods in aggregate macro F1, gaining 3.21% accuracy and 2.14% macro F1 over the respective strongest exemplar-free baselines. Under the Si-Blurry setting with recurring classes, AIR leads 15 exemplar-based and exemplar-free baselines, gaining 2.32% aggregate accuracy and 1.27% aggregate macro F1 over the strongest baseline. One-sided paired tests support positive mean absolute gains in these four comparisons (Holm-adjusted p<0.006).