Continual Learning for LLMs

LLM: Large Language Model

Ask about this topic

Overview

The field investigates how large language models can keep learning through continual pretraining, instruction tuning, alignment, and personalization without losing earlier knowledge or skills. Common approaches include replaying old or generated examples, distillation and regularization, selective or orthogonal parameter updates, modular adapters, and external memories that leave the model weights unchanged. Evaluations use sequential task suites such as TRACE and SuperNI, domain streams such as biomedical NLP, and evolving knowledge or user-interaction settings, measuring both new-task performance and retention over time. No single approach works reliably across settings: results depend on task order, model capacity, and update type, while long-term evaluation must balance adaptation, forgetting, transfer, safety, and compute cost.

Latest papers

CardsList

236 papers44 papers in the last four weeks, up 110% on the four weeks before. 0.3% of all new papers.

Apr 20, 2026

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from scratch is expensive and scales poorly, while continued training often degrades existing capabilities. We present BAR (Branch-Adapt-Route), which trains independent domain experts, each through its own mid-training, supervised finetuning, and reinforcement learning pipeline, and composes them via a Mixture-of-Experts architecture with lightweight router training. Unlike retraining approaches that mix all domains and require full reprocessing for any update (with cost scaling quadratically), BAR enables updating individual experts independently with linear cost scaling and no degradation to existing domains. At the 7B scale, with experts for math, code, tool use, and safety, BAR achieves an overall score of 49.1 (averaged across 7 evaluation categories), matching or exceeding re-training baselines (47.8 without mid-training, 50.5 with). We further show that modular training provides a structural advantage: by isolating each domain, it avoids the catastrophic forgetting that occurs when late-stage RL degrades capabilities from earlier training stages, while significantly reducing the cost and complexity of updating or adding a domain. Together, these results suggest that decoupled, expert-based training is a scalable alternative to monolithic retraining for extending language models.

Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia +3

University of Washington · Allen Institute for AI · University of California, Berkeley

Continual Learning for LLMsMixture-of-Experts Language ModelsLanguage Model Post-TrainingFine-Tuning Language ModelsMixture-of-Experts Fine-Tuning
AskPDF
Apr 20, 2026

HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation

Adapting foundation models under resource budgets relies heavily on Parameter-Efficient Fine-Tuning (PEFT), with LoRA being a standard modular solution. However, LoRA suffers from spectral interference. Low-rank updates often concentrate energy on the leading singular directions of pretrained weights, perturbing general capabilities and causing catastrophic forgetting and fragile multi-adapter merging. To resolve this, we propose HiP-LoRA, a spectrum-aware adaptation framework. Utilizing the cached singular value decomposition (SVD) of pretrained layers, HiP-LoRA decomposes updates into two channels: a principal channel within the dominant singular subspace, and a residual low-rank channel in the orthogonal complement. A singular-value-weighted stability budget on the principal channel continuously balances pretrained behavior preservation with task-specific plasticity. Experiments on Llama-3.1-8B demonstrate that under matched budgets, HiP-LoRA drastically reduces pretraining degradation and multi-adapter MergeFail, robustly outperforming baselines in interference-sensitive tasks like continual tuning and knowledge editing.

Lixian Chen, Jianhong Tan

Guangdong University of Technology

Continual Learning for LLMsLow-Rank AdaptationModel MergingParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Apr 20, 2026

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world deployment, where models undergo sequential adaptation across domains such as medicine, law, and code, causing safety guardrails to erode cumulatively. Yet all existing safety-preserving methods target only single-task fine-tuning, leaving the multi-domain sequential setting entirely unaddressed. We introduce SafeAnchor, a framework that anchors safety in place throughout continual adaptation. SafeAnchor first identifies low-rank safety subspaces in LoRA parameter space via Fisher Information eigendecomposition, then constrains domain-specific gradient updates to the orthogonal complement of these subspaces, and finally monitors for residual safety drift with threshold-triggered corrective replay. Evaluated on Llama-2-7B-Chat and Mistral-7B-Instruct across a three-domain pipeline and eight benchmarks, SafeAnchor retains 93.2% of original safety alignment, outperforming all baselines by 18-42 points, while matching unconstrained fine-tuning to within 1.5 points on domain tasks.

Dongxin Guo, Jikun Wu, Siu Ming Yiu

The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China

Continual Learning for LLMsLLM Fine-TuningLLM Safety AlignmentDomain Adaptation for LLMsGradient ProjectionSafety-Preserving Fine-Tuning of Language Models
AskPDF
Apr 19, 2026

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning

Large language models (LLMs) have demonstrated strong reasoning capabilities, and as existing approaches for enhancing LLM reasoning continue to mature, increasing attention has shifted toward meta-reasoning as a promising direction for further improvement. However, most existing meta-reasoning methods remain episodic: they focus on executing complex meta-reasoning routines within individual instances, but ignore the accumulation of reusable meta-reasoning skills across instances, leading to recurring failure modes and repeatedly high metacognitive effort. In this paper, we introduce Metacognitive Consolidation, a novel framework in which a model consolidates metacognitive experience from past reasoning episodes into reusable knowledge that improves future meta-reasoning. We instantiate this framework by structuring instance-level problem solving into distinct roles for reasoning, monitoring, and control to generate rich, attributable meta-level traces. These traces are then consolidated through a hierarchical, multi-timescale update mechanism that gradually forms evolving meta-knowledge. Experimental results demonstrate consistent performance gains across benchmarks and backbone models, and show that performance improves as metacognitive experience accumulates over time.

Ziqing Zhuang, Linhai Zhang, Jiasheng Si +2

Southeast University · King’s College London · Qilu University of Technology (Shandong Academy of Sciences) +1

Continual Learning for LLMsMeta-LearningLanguage Model Self-ImprovementMetacognition in Language ModelsLLM Reasoning
AskPDF
Apr 19, 2026

Continual Safety Alignment via Gradient-Based Sample Selection

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and commonsense reasoning. We investigate which training samples cause alignment drift through a data-centric lens. Our empirical analysis shows samples contribute unequally: high-gradient samples cause greater safety degradation and drive models toward pretrained distributions, while moderate-gradient samples enable task learning with minimal alignment loss. We propose gradient-based sample selection that filters high-gradient samples during fine-tuning. Across multiple model families on continual domain tasks, our method substantially improves alignment preservation while maintaining competitive task performance, without requiring curated safe data or architectural modifications. Our method is robust across selection ratios, task orderings, and diverse attack benchmarks.

Thong Bach, Dung Nguyen, Thao Minh Le +1

Applied Artificial Intelligence Initiative (A2I2), Deakin University · Pennsylvania State University

Continual Learning for LLMsLLM Fine-TuningLLM Safety AlignmentTraining Data SelectionSelective Fine-TuningSafety-Preserving Fine-Tuning of Language Models
AskPDF
Apr 18, 2026

Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization

Large Language Models (LLMs) have demonstrated excellent performance in general language understanding, generation and other tasks. However, when fine-tuning for specific domain tasks, the general knowledge accumulated in the pre-training phase is often partially overwritten or forgotten due to parameter updates, which severely limits the generalization ability and transferability of LLMs. Traditional fine-tuning strategies mostly train on the entire parameter space, ignoring the heterogeneity of model parameters, that is, some parameters are extremely important for general tasks, while other parameters are more sensitive to specific tasks. To alleviate the above problems, this paper innovatively proposes a parameter element importance evaluation method, which divides parameters into "core parameters" and "non-core parameters" by distinguishing the importance of parameters for general language ability tasks and specific domain tasks, and fixes the core parameters during fine-tuning, and only fine-tunes the non-core parameters. Extensive experiments on scientific, medical and physical tasks using GPT-J and LLaMA-3 show that our method can mitigate catastrophic forgetting while enhancing the adaptability of the model.

Weijie Wan, Jiangjiang Zhao

Shortest Path Technology · China Mobile Communications Group Co.,Ltd

Continual Learning for LLMsLLM Fine-TuningDomain Adaptation for LLMsSelective Fine-TuningParameter-Efficient Fine-Tuning
AskPDF
Apr 17, 2026

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.

Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau +6

Bitdefender · ETH Zurich · University of Bucharest

Continual Learning for LLMsLow-Rank AdaptationSparse Fine-TuningParameter-Efficient Fine-TuningAdapter-Based Continual LearningContinual LoRA
AskPDF
Apr 16, 2026

Why Fine-Tuning Encourages Hallucinations and How to Fix It

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t.~knowledge acquired during pre-training. Since these errors arise as a by-product of knowledge degradation, we explore whether established continual learning tools can mitigate them. We propose a self-distillation-based SFT method that facilitates effective factual learning while minimizing hallucinations w.r.t.~pre-existing knowledge by regularizing output-distribution drift. We also show that when new knowledge acquisition is unnecessary, suppressing factual plasticity by freezing parameter groups preserves task performance while reducing hallucinations. Lastly, we investigate the mechanism, contrasting capacity limitations, behavior cloning, and localized interference. Our experiments show that a main driver is interference among overlapping semantic representations, which self-distillation mitigates and an associative-memory model explains: forgetting grows with the overlap between new and stored facts.

Guy Kaplan, Zorik Gekhman, Zhen Zhu +5

♡Hebrew University of Jerusalem · ♣Technion – Israel Institute of Technology · ♢University of Illinois Urbana-Champaign +1

Supervised Fine-TuningContinual Learning for LLMsLLM Hallucination MitigationHallucination in Language ModelsSelf-DistillationCatastrophic Forgetting
AskPDF
Apr 16, 2026

Discovering Novel LLM Experts via Task-Capability Coevolution

Frontier model developers aim to train models continually to possess emergent, diverse capabilities. To extend capabilities, the current pre-training and post-training paradigm requires manually starting training runs with static datasets or reward functions every time. Addressing this limitation, our work pursues the insight that open-endedness (via the coevolution of models and tasks) can discover models with increasingly novel skills in a single run. We introduce a new model development framework that extends coevolution to large language model (LLM) discovery, open-ended Assessment Coevolving with Diverse Capabilities (AC/DC). AC/DC evolves both LLMs via model merging and natural language tasks via synthetic data generation. AC/DC discovers growing archives of LLMs that surpass the capabilities of larger LLMs while taking up less GPU memory. In particular, our LLM populations achieve a broader Coverage of expertise than other curated models or baselines on downstream benchmarks, without any explicit benchmark optimization. Furthermore, AC/DC improves Coverage over time, continually innovates on tasks and models, and improves performance in multi-agent best-of-N selection. Our findings highlight the potential of coevolution as a means of discovering broader sets of capabilities from base LLMs. Overall, AC/DC brings us one step closer to a profoundly new paradigm of LLM development, where continual improvements to the diversity of model capabilities can be accelerated by leveraging existing models as stepping stones to increasingly powerful models.

Andrew Dai, Boris Meinardus, Ciaran Regan +2

Sakana AI

Continual Learning for LLMs
AskPDF
Apr 15, 2026

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning

Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-critical parameters during training. However, these methods represent a static solution to a dynamic problem, assuming that parameter importance remains fixed once identified. In this work, we empirically demonstrate that parameter importance exhibits temporal drift over the course of training. To address this, we propose Evolving Parameter Isolation (EPI), a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. Instead of freezing a fixed subset of parameters, EPI periodically updates isolation masks using gradient-based signals, enabling the model to protect emerging task-critical parameters while releasing outdated ones to recover plasticity. Experiments on diverse multi-task benchmarks demonstrate that EPI consistently reduces interference and forgetting compared to static isolation and standard fine-tuning, while improving overall generalization. Our analysis highlights the necessity of synchronizing isolation mechanisms with the evolving dynamics of learning diverse abilities.

Zekai Lin, Chao Xue, Di Liang +8

Tencent Hunyuan · University of New South Wales · Tencent Yuanbao +2

Supervised Fine-TuningSelective Fine-TuningCatastrophic ForgettingContinual Learning for LLMs
AskPDF
Apr 13, 2026

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter perturbations to a static and dense set of LLM layers for all editing instances. This practice is counter-intuitive, as we hypothesize that different pieces of knowledge are stored in distinct layers of the model. Neglecting this layer-wise specificity can impede adaptability in integrating new knowledge and result in catastrophic forgetting for both general and previously edited knowledge. To address this, we propose HiEdit, a hierarchical reinforcement learning framework that adaptively identifies the most knowledge-relevant layers for each editing instance. By enabling dynamic, instance-aware layer selection and incorporating an intrinsic reward for sparsity, HiEdit achieves precise, localized updates. Experiments on various LLMs show that HiEdit boosts the performance of the competitive RLEdit by an average of 8.48% with perturbing only half of the layers per edit. Our code is available at: https://github.com/yangfanww/hiedit.

Yangfan Wang, Tianyang Sun, Chen Tang +3

Harbin Institute of Technology · AI Research Center, Midea Group (Shanghai) Co., Ltd. · State Key Laboratory of Smart Farm Technologies and Systems +1

Model EditingLanguage Model EditingContinual Learning for LLMsContinual Learning
AskPDF
Apr 7, 2026

In-Place Test-Time Training

The static train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT) offers a compelling alternative by updating a subset of model parameters (fast weights) at inference time, yet its potential in the current LLM ecosystem is hindered by critical barriers including architectural incompatibility, computational inefficiency and misaligned fast weight objectives for language modeling. In this work, we introduce In-Place Test-Time Training (In-Place TTT), a framework that seamlessly endows LLMs with Test-Time Training ability. In-Place TTT treats the final projection matrix of the ubiquitous MLP blocks as its adaptable fast weights, enabling a drop-in" enhancement for LLMs without costly retraining from scratch. Furthermore, we replace TTT's generic reconstruction objective with a tailored, theoretically-grounded objective explicitly aligned with the Next-Token-Prediction task governing autoregressive language modeling. This principled objective, combined with an efficient chunk-wise update mechanism, results in a highly scalable algorithm compatible with context parallelism. Extensive experiments validate our framework's effectiveness: as an in-place enhancement, it enables a 4B-parameter model to achieve superior performance on tasks with contexts up to 128k, and when pretrained from scratch, it consistently outperforms competitive TTT-related approaches. Ablation study results further provide deeper insights on our design choices. Collectively, our results establish In-Place TTT as a promising step towards a paradigm of continual learning in LLMs.

Guhao Feng, Shengjie Luo, Kai Hua +4

ByteDance Seed · Peking University

Test-Time TrainingContinual Learning for LLMsLong-Context Language Model Inference
AskPDF
Apr 6, 2026

Improving Sparse Memory Finetuning

Large Language Models (LLMs) are typically static after training, yet real-world applications require continual adaptation to new knowledge without degrading existing capabilities. Standard approaches to updating models, like full finetuning or parameter-efficient methods (e.g., LoRA), face a fundamental trade-off: catastrophic forgetting. They modify shared dense representations, causing interference across tasks. Sparse Memory Finetuning (SMF) offers a promising alternative by localizing updates to a small subset of parameters in explicit memory layers. In this work, we present an open-source pipeline to retrofit existing pretrained models (Qwen-2.5-0.5B) with sparse memory modules, enabling effective continual learning on consumer hardware. We extend prior work by introducing a theoretically grounded slot-selection mechanism based on Kullback-Leibler (KL) divergence, which prioritizes memory updates for informationally "surprising" tokens relative to a background distribution. Our experiments demonstrate that our retrofitted models can acquire new factual knowledge with minimal forgetting of held-out capabilities, validating the sparse update hypothesis in a practical setting.

Satyam Goyal, Anirudh Kanchi, Garv Shah +1

University of Michigan, Ann Arbor

Continual Learning for LLMsSparse Fine-TuningMemory-Augmented Language ModelsParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Apr 6, 2026

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although existing approaches, such as continual finetuning, knowledge editing, and retrieval-augmented generation (RAG), aim to update or supplement model knowledge, they are rarely evaluated in settings that reflect chronological, evolving, and real-world knowledge evolution. In this work, we introduce a new benchmark of real-world dynamic events, constructed from time-stamped evidence that captures how knowledge evolves over time, which enables systematic evaluation of model adaptation under continuous knowledge drift. The benchmark reveals that most existing methods, including vanilla RAG and several learning-based approaches, struggle under this setting, exposing critical limitations such as catastrophic forgetting and temporal inconsistency. To mitigate these limitations, we propose a time-aware retrieval baseline, Chronos, which progressively organizes retrieved evidence into an Event Evolution Graph to enable more temporally consistent understanding in LLMs without additional training. Overall, this work provides a foundation for analyzing and advancing LLM adaptation to continuous knowledge drift in realistic settings.

Hanbing Liu, Lang Cao, Yang Li

Tsinghua University; Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University · University of Illinois Urbana-Champaign · School of Artificial Intelligence, Chinese University of Hong Kong (Shenzhen)

Retrieval-Augmented GenerationContinual Learning for LLMsLLM EvaluationTemporal Reasoning in Language Models
AskPDF
Apr 6, 2026

GAIN: Multiplicative Modulation for Domain Adaptation

Adapting LLMs to new domains causes forgetting because standard methods (e.g., full fine-tuning, LoRA) inject new directions into the weight space. We show that forgetting is governed by one algebraic property: whether the update preserves the column span of the pretrained weight matrix (Proposition 1). We propose GAIN, the simplest multiplicative alternative (W_new = S * W), which satisfies this by construction and can be absorbed into existing weights for zero inference cost. Across five models (774M to 70B) adapted sequentially over eight domains, GAIN improves earlier-domain perplexity by 7-13%, while LoRA degrades it by 18-36%. GAIN matches replay-augmented LoRA without storing prior data and dominates EWC on the forgetting-adaptation Pareto front. While LoRA can only reduce forgetting by sacrificing in-domain adaptation, GAIN achieves both with no domain boundaries and no regularization. The principle generalises: (IA)^3, an independent multiplicative method, also improves earlier domains.

Hengshuai Yao, Xing Chen, Ahmed Murtadha +1

Sapient Intelligence · Department of Computing Science, University of Alberta

Domain Adaptation for LLMsContinual Learning for LLMsCatastrophic Forgetting
AskPDF
Apr 2, 2026

Autolearn: Learn by Surprise, Commit by Proof

We propose Autolearn, a framework that enables language models to learn from documents they read, with no external supervision. Passages that produce anomalously high per-token loss are flagged, verified through a self-generated Q&A chain, and trained on with conviction-proportional β2β_2 adjustment. We introduce the perturbation gap (paraphrase-to-original perplexity ratio) as a metric that distinguishes memorization from understanding. The key mechanism is the training data format: Q&A-format training drives the perturbation gap below the pre-trained baseline (2.098 vs. 2.204, Δ=−0.106Δ= -0.106, >10σ> 10σ), suppressing token-sequence memorization, while standard fine-tuning's best attempt remains within noise (Δ=−0.010Δ= -0.010, <1σ< 1σ). Across four models spanning Qwen3 and Phi-4 families, Autolearn is the only method that enters this regime. Stochastic evaluation reveals passage-specific knowledge acquisition: the probability of generating a correct novel fact rises from 6% to 54% after training (p<10−4p < 10^{-4}), and Q&A format outperforms standard fine-tuning on genuinely novel facts. The system is self-extinguishing: learned content reduces surprisal below threshold and is skipped on re-encounter.

Kang-Sin Choi

Ewha Womans University

Online Language Model AdaptationKnowledge Augmentation for Language ModelsSelf-Training for Language ModelsMemorization in Language ModelsContinual Learning for LLMs
AskPDF
Apr 1, 2026

Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning

We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference. Five interlocking components: (1) MoE-LoRA with Shazeer-style noisy top-2 routing across all seven transformer projections under QLoRA 4-bit quantization with rsLoRA scaling; (2) an inner loop performing residual boosting by freezing trained stacks and adding new ones; (3) an outer loop training sequential domain-specific stacks with curriculum-ordered dependencies; (4) null-space projection via randomized SVD constraining new stacks to subspaces orthogonal to prior directions, achieving zero forgetting in isolation; (5) an outcome-based sigmoid meta-router trained on empirically discovered domain-combination targets that selectively weights stacks, enabling cross-domain composition. Two boundary experiments: (6) PSN pretraining on a randomly initialized model; (7) per-domain RL (DPO/GRPO) validating compatibility with post-SFT alignment. Validated on TinyLlama-1.1B (4 domains, 9 stacks) and Gemma 3 12B IT (5 domains, 10 stacks), MoE-LoRA achieves 2.5x faster convergence than parameter-matched single LoRA, residual boosting breaks through the single-stack ceiling, and the routed system recovers generation quality destroyed by ungated stack accumulation. The central finding: the outcome-based router discovers that domain stacks encode transferable cognitive primitives (instruction-following clarity, numerical reasoning, procedural logic, chain-of-thought structure) rather than domain-specific knowledge, with medical prompts routing to chat+math stacks in 97% of cases despite zero medical data in those stacks.

Mohammad R. Abu Ayyash

Brains Build Research, Ramallah, Palestine

Continual Learning for LLMsLLM Fine-TuningCross-Domain Transfer LearningMixture-of-Experts Language Models
AskPDF
Mar 29, 2026

Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder fine-tuning with companion representation probes that test a frozen-backbone explanation of its robustness. In five full-validation BERT-base reruns on an RTE->MRPC->CoLA->SST-2 sequence, full fine-tuning yields 19.9%+/-4.8% average forgetting, whereas standard LoRA (r=8, query/value modules) yields 0.6%+/-1.4% (paired t-test, p=0.002, Cohen's d_s=3.12). Task-level analyses confirm this reduction is not merely an aggregate effect. Secondary experiments on RoBERTa-base show the same pattern, and the strongest EWC baseline remains at 15.5%+/-1.4% forgetting. A six-task extension reveals that low average forgetting can hide strong task-level heterogeneity. Fine-grained freezing ablations show a marked forgetting drop once frozen parameters exceed roughly 95%, with classifier-only and shallow-adapter baselines approaching LoRA. Companion task-similarity probes in GPT-2 and RoBERTa show the same directional story: frozen-backbone regimes preserve higher inter-task similarity than full fine-tuning, gradual unfreezing weakens stability, and full fine-tuning exhibits its clearest divergence at the final transformer layer. These results support a restrained mechanistic interpretation: LoRA helps largely because backbone freezing preserves a more stable shared feature scaffold. We position standard LoRA as both a strong empirical baseline for sequential encoder adaptation and a useful probe of how selective plasticity shapes interference in transformer continual learning.

Ashish Pandey

Catastrophic ForgettingLow-Rank AdaptationContinual Learning for LLMs
AskPDF
Mar 24, 2026

MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis

Existing LLM-based Kubernetes diagnostic systems cannot learn from operational experience, operating on static knowledge bases without improving from past resolutions. We present MetaKube, an experience-aware LLM framework through three synergistic innovations: (1) an Episodic Pattern Memory Network (EPMN) that abstracts diagnostic patterns from historical resolutions and provides confidence-calibrated retrieval for both rapid pattern matching and guided causal exploration, (2) a meta-cognitive controller that dynamically routes between intuitive and analytical pathways based on problem familiarity, optimizing the trade-off between speed and depth, and (3) KubeLLM, a locally-deployable 8B model enhanced through domain-specific post-training on our 7,000-sample Kubernetes Fault Resolution Dataset. Evaluation on 1,873 real-world scenarios demonstrates MetaKube transforms Qwen3-8B from 50.9 to 90.5 points, approaching GPT-4.1 performance while ensuring complete data privacy. EPMN contributes 15.3% improvement through experiential learning, with continuous learning experiments showing progressive gains as the system accumulates operational knowledge. The source code and related resources are available at https://github.com/MetaKube-LLM-for-Kubernetes-Diagnosis/MetaKube.

Wei Sun, Ting Wang, Xinran Tian +4

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen; Shenzhen Future Network of Intelligence Institute, Shenzhen, China · Shenzhen Future Network of Intelligence Institute, Shenzhen, China · China Mobile Communications Group Guangdong Co., Ltd., Guangzhou, China

Fault DiagnosisContinual Learning for LLMs
AskPDF
Mar 23, 2026

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation. Traditional fine-tuning (FT) struggles to adapt to non-stationary data streams without resulting in catastrophic for getting or requiring extensive manual data curation. To address these limitations within the streaming and continual learning paradigm, we propose the Self-Optimizing Lifelong Autonomous Reasoner (SOLAR) which is an open-ended autonomous agent that leverages parameter-level meta-learning to self-improve, treating model weights as an environment for exploration. It initiates the process by consolidating a strong prior over common-sense knowledge making it effective for transfer-learning. By utilizing a multi-level reinforcement learning approach, SOLAR autonomously discovers adaptation strategies, enabling efficient test-time adaptation to unseen domains. Crucially, SOLAR maintains an evolving knowledge base of valid modification strategies, implicitly acting as an episodic memory buffer to balance plasticity (adaptation to new tasks) and stability (retention of meta-knowledge). Experiments demonstrate that SOLAR outperforms strong baselines on common-sense, mathematical, medical, coding, social and logical reasoning tasks, marking a significant step toward autonomous agents capable of lifelong adaptation in evolving environments.

Nitin Vetcha, Dianbo Liu

Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore · Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, India

Continual Learning for LLM AgentsContinual Learning for LLMsRL for LLM AgentsMeta-LearningTest-Time AdaptationMemory-Augmented Language Model Agents
AskPDF
Mar 17, 2026

Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training

A foundational principle in cognitive science holds that intelligent agents do not learn by storing experiences as isolated instances, but by forming abstract schemas that capture relational structure shared across situations. Even though this claim is well supported by behavioral and neuroimaging studies, its role as a computational training signal in language models remains underexplored. We target this gap in the setting of non-stationary language model training, asking does biasing learning toward structural abstraction reduce catastrophic interference and improve relational generalization as predicted by human results? To study this question, we introduce Abstraction-Augmented Training (AAT), a lightweight loss-level modification that jointly optimizes over concrete instances and their structural abstractions, and two benchmarks, the Relational Cycle Benchmark (RCB) and the Narrative Abstraction Benchmark (NAB). These resources operationalize core cognitive constructs: entity masking as a computational analog of relational alignment, and proverbs as vehicles for implicit abstract meaning that must be inferred across surface-dissimilar situations. Our empirical results demonstrate that AAT consistently reduces forgetting and improves generalization in a pattern that aligns with cognitive predictions for schema-based learning. Beyond the practical implications for continual learning, these results offer preliminary computational evidence that structural abstraction is a signal for stable learning in non-stationary environments.

Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati +2

University of Southern California

LLM TrainingContinual Learning for LLMsCatastrophic Forgetting
AskPDF
Mar 17, 2026

Online Experiential Learning for Language Models

The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose Online Experiential Learning (OEL), a framework that enables language models to continuously improve from their own deployment experience. OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side; second, this knowledge is consolidated into model parameters via on-policy context distillation, requiring no access to the user-side environment. The two stages are iterated to form an online learning loop, where the improved model collects higher-quality trajectories that yield richer experiential knowledge for subsequent rounds. We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants. OEL achieves consistent improvements over successive iterations, enhancing both task accuracy and token efficiency while preserving out-of-distribution performance. Our analysis further shows that extracted experiential knowledge is significantly more effective than raw trajectories, and that on-policy consistency between the knowledge source and the policy model is critical for effective learning.

Tianzhu Ye, Li Dong, Qingxiu Dong +3

Microsoft Research

Continual Learning for LLMsLanguage Model Self-Improvement
AskPDF
Mar 17, 2026

MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learning

Medical language models must be updated as evidence and terminology evolve, yet sequential updating can trigger catastrophic forgetting. Although biomedical NLP has many static benchmarks, no unified, task-diverse benchmark exists for evaluating continual learning under standardized protocols, robustness to task order and compute-aware reporting. We introduce MedCL-Bench, which streams ten biomedical NLP datasets spanning five task families and evaluates eleven continual learning strategies across eight task orders, reporting retention, transfer, and GPU-hour cost. Across backbones and task orders, direct sequential fine-tuning on incoming tasks induces catastrophic forgetting, causing update-induced performance regressions on prior tasks. Continual learning methods occupy distinct retention-compute frontiers: parameter-isolation provides the best retention per GPU-hour, replay offers strong protection at higher cost, and regularization yields limited benefit. Forgetting is task-dependent, with multi-label topic classification most vulnerable and constrained-output tasks more robust. MedCL-Bench provides a reproducible framework for auditing model updates before deployment.

Min Zeng, Shuang Zhou, Zaifu Zhan +1

Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, 55455, MN, USA.

Continual LearningContinual Learning for LLMsCatastrophic ForgettingReplay-Based Continual Learning
AskPDF
Mar 17, 2026

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a proof-of-concept pilot study showing that persistent memory in the continuous latent space of a frozen LLM is feasible -- even under severe resource constraints (a single frozen Flan-T5-XL backbone, small trainable adapters, a single dataset). We implement six architectural methods spanning three injection points and four write mechanisms; unlike text-level memory systems, every write and read is a differentiable operation on dense vectors. After training only the adapter, the memory bank continues to accumulate at inference time without gradients, enabling conversational learning. Under a forgetting-curve evaluation on LoCoMo at two capacity scales (1×\times and 10×\times), the stateless baseline scores exactly zero; at 10×\times all six trained adapters produce positive memory-recall curves; at 1×\times three methods collapse, revealing capacity as a critical design parameter. Because the memory bank is a compact numerical array, it can be scaled to arbitrarily large capacity without altering the backbone. We argue that full end-to-end training with larger models, larger data, and orders-of-magnitude larger memory will yield substantially stronger results; this pilot study establishes the feasibility baseline and design-space taxonomy that such efforts require.

Hong Jeong

Inha University in Tashkent, Uzbekistan

Persistent Memory for Language ModelsMemory-Augmented Language ModelsContinual Learning for LLMs
AskPDF
Mar 16, 2026

SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing

Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black boxes and relies on coarse-grained parameter interventions that inevitably disrupt preserved knowledge. To address this, we propose SCAN (a sparse editing framework based on Sparse Circuit Anchored Neuron) which transforms editing into a mechanism-aware manipulation by constructing a knowledge circuit via Sparse Transcoders. Experiments on Gemma2, Qwen3, and Llama3.1 across CounterFact, ZsRE and WikiFactDiff demonstrate that SCAN achieves a superior performance, maintaining model integrity on benchmarks like MMLU and GSM8K even after 3,000 sequential edits, whereas other existing methods deteriorate progressively as editing accumulates, eventually resulting in model collapse.

Yuhuan Liu, Haitian Zhong, Xinyuan Xia +3

New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences · Cuiying Honors College, Lanzhou University · Zhongguancun Academy +1

Knowledge EditingLanguage Model EditingCatastrophic ForgettingContinual Learning for LLMs
AskPDF
Mar 13, 2026

Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs. This paper presents a comprehensive overview of CL methodologies tailored for LLMs, structured around three core training stages: continual pre-training, continual fine-tuning, and continual alignment. Beyond the canonical taxonomy of rehearsal-, regularization-, and architecture-based methods, we further subdivide each category by its distinct forgetting mitigation mechanisms and conduct a rigorous comparative analysis of the adaptability and critical improvements of traditional CL methods for LLMs. In doing so, we explicitly highlight core distinctions between LLM CL and traditional machine learning, particularly with respect to scale, parameter efficiency, and emergent capabilities. Our analysis covers essential evaluation metrics, including forgetting rates and knowledge transfer efficiency, along with emerging benchmarks for assessing CL performance. While current methods show promising results, fundamental challenges persist in achieving seamless knowledge integration, and we identify key open problems and future directions for the field.

Hongyang Chen, Zhongwu Sun, Hongfei Ye +2

Zhejiang Lab, Hangzhou 311100, China

Continual Learning for LLMsCatastrophic ForgettingLanguage Model PretrainingLLM Alignment
AskPDF
Mar 13, 2026

From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning

Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems. We propose Kalman World Models (KWM), a class of learned state-space models trained via recursive Bayesian filtering rather than reverse-mode automatic differentiation. Instead of gradient descent updates, we replace parameter learning with Kalman-style gain adaptation. Training becomes online filtering; error signals become innovations. We further extend this framework to transformer-based large language models (LLMs), where internal activations are treated as latent dynamical states corrected via innovation terms. This yields a gradient-free training and adaptation paradigm grounded in control theory. We derive stability conditions, analyze computational complexity, and provide empirical results on sequence modeling tasks demonstrating competitive performance with improved robustness and continual adaptation properties.

Andrew Kiruluta

UC Berkeley School of Information

Gradient-Free OptimizationState Space ModelsWorld Model LearningKalman FilteringContinual Learning for LLMs
AskPDF
Mar 12, 2026

NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation

Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly Low-Rank Adaptation (LoRA), have become essential for adapting Large Language Models (LLMs) to downstream tasks. While the recent FlyLoRA framework successfully leverages bio-inspired sparse random projections to mitigate parameter interference, it relies on a static, magnitude-based routing mechanism that is agnostic to input context. In this paper, we propose NeuroLoRA, a novel Mixture-of-Experts (MoE) based LoRA framework inspired by biological neuromodulation -- the dynamic regulation of neuronal excitability based on context. NeuroLoRA retains the computational efficiency of frozen random projections while introducing a lightweight, learnable neuromodulation gate that contextually rescales the projection space prior to expert selection. We further propose a Contrastive Orthogonality Loss to explicitly enforce separation between expert subspaces, enhancing both task decoupling and continual learning capacity. Extensive experiments on MMLU, GSM8K, and ScienceQA demonstrate that NeuroLoRA consistently outperforms FlyLoRA and other strong baselines across single-task adaptation, multi-task model merging, and sequential continual learning scenarios, while maintaining comparable parameter efficiency.

Yuxin Yang, Haoran Zhang, Mingxuan Li +6

Shanghai University · Fudan University

Parameter-Efficient Fine-TuningLow-Rank AdaptationMulti-Task LearningContinual Learning for LLMs
AskPDF
Mar 11, 2026

Reversible Lifelong Model Editing via Semantic Routing-Based LoRA

The dynamic evolution of real-world necessitates model editing within Large Language Models. While existing methods explore modular isolation or parameter-efficient strategies, they still suffer from semantic drift or knowledge forgetting due to continual updating. To address these challenges, we propose SoLA, a Semantic routing-based LoRA framework for lifelong model editing. In SoLA, each edit is encapsulated as an independent LoRA module, which is frozen after training and mapped to input by semantic routing, allowing dynamic activation of LoRA modules via semantic matching. This mechanism avoids semantic drift caused by cluster updating and mitigates catastrophic forgetting from parameter sharing. More importantly, SoLA supports precise revocation of specific edits by removing key from semantic routing, which restores model's original behavior. To our knowledge, this reversible rollback editing capability is the first to be achieved in existing literature. Furthermore, SoLA integrates decision-making process into edited layer, eliminating the need for auxiliary routing networks and enabling end-to-end decision-making process. Extensive experiments demonstrate that SoLA effectively learns and retains edited knowledge, achieving accurate, efficient, and reversible lifelong model editing.

Haihua Luo, Xuming Ran, Tommi Kärkkäinen +4

Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland · National University of Singapore, Singapore · School of Computer Science and Technology, Dalian University of Technology, Dalian, China

Model EditingLanguage Model EditingContinual Learning for LLMsLow-Rank Adaptation
AskPDF
Mar 10, 2026

MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning

Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolve over time. While strong adaptability enables rapid acquisition of new knowledge, it also exposes LLMs to catastrophic forgetting, where previously learned skills degrade during sequential training. Existing replay-based strategies, such as fixed interleaved replay, accuracy-supervised, and loss-driven scheduling, remain limited: some depend on heuristic rules and provide only partial mitigation of forgetting, while others improve performance but incur substantial computational overhead. Motivated by retention dynamics under sequential fine-tuning, we propose Memory-Inspired Sampler and Scheduler Replay (MSSR), an experience replay framework that estimates sample-level memory strength and schedules rehearsal at adaptive intervals to mitigate catastrophic forgetting while maintaining fast adaptation. Extensive experiments across three backbone models and 11 sequential tasks show that MSSR consistently outperforms state-of-the-art replay baselines, with particularly strong gains on reasoning-intensive and multiple-choice benchmarks.

Yiyang Lu, Yu He, Jianlong Chen +1

The Chinese University of Hong Kong, Shenzhen · Nanjing University

Continual Learning for LLMsReplay-Based Continual LearningCatastrophic Forgetting
AskPDF