A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic forgetting. Previous work within the dominant pretrain-then-finetune paradigm has explored parameter-efficient fine-tuning for single-task adaptation, effectively steering a frozen pretrained model with a small number of parameters. However, in the context of lifelong learning, these methods rely on the impractical assumption of a test-time task identifier and restrict knowledge sharing among isolated adapters. To address these limitations, we propose Dynamic Mixture of Progressive Parameter-Efficient Expert Library (DMPEL) for lifelong robot learning. DMPEL progressively learn a low-rank expert library and employs a lightweight router to dynamically combine experts into an end-to-end policy, facilitating flexible behavior during lifelong adaptation. Moreover, by leveraging the modular structure of the fine-tuned parameters, we introduce coefficient replay to guide the router in accurately retrieving frozen experts for previously encountered tasks, thereby mitigating catastrophic forgetting. This method is significantly more storage- and computationally-efficient than applying demonstration replay to the entire policy. Extensive experiments on the lifelong manipulation benchmark LIBERO demonstrate that our framework outperforms state-of-the-art lifelong learning methods in success rates across continual adaptation, while utilizing minimal trainable parameters and storage.
Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer strong reasoning but face challenges in representation, control, and real-world evaluation. To address these challenges, we present LiloDriver, a lifelong learning framework for closed-loop motion planning in long-tail autonomous driving scenarios. By integrating large language models (LLMs) with a memory-augmented planner generation system, LiloDriver continuously adapts to new scenarios without retraining. It features a four-stage architecture including perception, scene encoding, memory-based strategy refinement, and LLM-guided reasoning. Evaluated on the nuPlan benchmark, LiloDriver achieves superior performance in both common and rare driving scenarios, outperforming static rule-based and learning-based planners. Our results highlight the effectiveness of combining structured memory and LLM reasoning to enable scalable, human-like motion planning in real-world autonomous driving. Our code is available at https://github.com/Hyan-Yao/LiloDriver.
Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing benchmarks treat agents as static systems and fail to evaluate lifelong learning capabilities. We present LifelongAgentBench, the first unified benchmark designed to systematically assess the lifelong learning ability of LLM agents. It provides skill-grounded, interdependent tasks across three interactive environments, Database, Operating System, and Knowledge Graph, with automatic label verification, reproducibility, and modular extensibility. Extensive experiments reveal that conventional experience replay has limited effectiveness for LLM agents due to irrelevant information and context length constraints. We further introduce a group self-consistency mechanism that significantly improves lifelong learning performance. We hope LifelongAgentBench will advance the development of adaptive, memory-capable LLM agents.
Lifelong learning enables large language models (LLMs) to adapt to evolving information by continually updating their internal knowledge. An ideal system should support efficient, wide-ranging updates while preserving existing capabilities and ensuring reliable deployment. Model editing stands out as a promising solution for this goal, offering a focused and efficient way to revise a model's internal knowledge. Although recent paradigms have made notable progress, they often struggle to meet the demands of practical lifelong adaptation at scale. To bridge this gap, we propose ULTRAEDIT-a fundamentally new editing solution that is training-, subject- and memory-free, making it particularly well-suited for ultra-scalable, real-world lifelong model editing. ULTRAEDIT performs editing through a self-contained process that relies solely on lightweight linear algebra operations to compute parameter shifts, enabling fast and consistent parameter modifications with minimal overhead. To improve scalability in lifelong settings, ULTRAEDIT employs a lifelong normalization strategy that continuously updates feature statistics across turns, allowing it to adapt to distributional shifts and maintain consistency over time. ULTRAEDIT achieves editing speeds over 7x faster than the previous state-of-the-art method-which was also the fastest known approach-while consuming less than 1/3 the VRAM, making it the only method currently capable of editing a 7B LLM on a 24GB consumer-grade GPU. Furthermore, we construct ULTRAEDITBENCH-the largest dataset in the field to date, with over 2M editing pairs-and demonstrate that our method supports up to 1M edits while maintaining high accuracy. Comprehensive experiments on four datasets and six models show that ULTRAEDIT consistently achieves superior performance across diverse model editing scenarios. Our code is available at: https://github.com/XiaojieGu/UltraEdit.
Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimizers with higher performance than classic human-designed optimizers. However, existing MetaBBO methods conduct one-off training under the assumption that a stationary problem distribution with extensive and representative training problem samples is pre-available. This assumption is often impractical in real-world scenarios, where diverse problems following shifting distribution continually arise. Consequently, there is a pressing need for methods that can continuously learn from new problems encountered on-the-fly and progressively enhance their capabilities. In this work, we explore a novel paradigm of lifelong learning in MetaBBO and introduce LiBOG, a novel approach designed to learn from sequentially encountered problems and generate high-performance optimizers for Black-Box Optimization (BBO). LiBOG consolidates knowledge both across tasks and within tasks to mitigate catastrophic forgetting. Extensive experiments demonstrate LiBOG's effectiveness in learning to generate high-performance optimizers in a lifelong learning manner, addressing catastrophic forgetting while maintaining plasticity to learn new tasks.
Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective of simultaneously preventing catastrophic forgetting and allowing forward knowledge transfer during task-incremental learning, while ensuring exact task unlearning and minimizing memory requirements, based on a single neural network model to be adapted. Our proposed solution, privacy-aware lifelong learning (PALL), involves optimization of task-specific sparse subnetworks with parameter sharing within a single architecture. We additionally utilize an episodic memory rehearsal mechanism to facilitate exact unlearning without performance degradations. We empirically demonstrate the scalability of PALL across various architectures in image classification, and provide a state-of-the-art solution that uniquely integrates lifelong learning and privacy-aware unlearning mechanisms for responsible AI applications.
Building a generalizable self-correction system is crucial for robots to recover from failures. Despite advancements in Multimodal Large Language Models (MLLMs) that empower robots with semantic reflection ability for failure, translating semantic reflection into how to correct fine-grained robotic actions remains a significant challenge. To address this gap, we build the Phoenix framework, which leverages motion instruction as a bridge to connect high-level semantic reflection with low-level robotic action correction. In this motion-based self-reflection framework, we start with a dual-process motion adjustment mechanism with MLLMs to translate the semantic reflection into coarse-grained motion instruction adjustment. To leverage this motion instruction for guiding how to correct fine-grained robotic actions, a multi-task motion-conditioned diffusion policy is proposed to integrate visual observations for high-frequency robotic action correction. By combining these two models, we could shift the demand for generalization capability from the low-level manipulation policy to the MLLMs-driven motion adjustment model and facilitate precise, fine-grained robotic action correction. Utilizing this framework, we further develop a lifelong learning method to automatically improve the model's capability from interactions with dynamic environments. The experiments conducted in both the RoboMimic simulation and real-world scenarios prove the superior generalization and robustness of our framework across a variety of manipulation tasks. Our code is released at \href{https://github.com/GeWu-Lab/Motion-based-Self-Reflection-Framework}{https://github.com/GeWu-Lab/Motion-based-Self-Reflection-Framework}.
Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal-based and rehearsal-free methods to address this challenge. Rehearsal-based approaches rely on knowledge distillation, continuously accumulating forgetting during the distillation process. Rehearsal-free methods insufficiently learn the distribution of each domain, leading to forgetfulness over time. To solve these issues, we propose a novel Distribution-aware Forgetting Compensation (DAFC) model that explores cross-domain shared representation learning and domain-specific distribution integration without using old exemplars or knowledge distillation. We propose a Text-driven Prompt Aggregation (TPA) that utilizes text features to enrich prompt elements and guide the prompt model to learn fine-grained representations for each instance. This can enhance the differentiation of identity information and establish the foundation for domain distribution awareness. Then, Distribution-based Awareness and Integration (DAI) is designed to capture each domain-specific distribution by a dedicated expert network and adaptively consolidate them into a shared region in high-dimensional space. In this manner, DAI can consolidate and enhance cross-domain shared representation learning while alleviating catastrophic forgetting. Furthermore, we develop a Knowledge Consolidation Mechanism (KCM) that comprises instance-level discrimination and cross-domain consistency alignment strategies to facilitate model adaptive learning of new knowledge from the current domain and promote knowledge consolidation learning between acquired domain-specific distributions, respectively. Experimental results show that our DAFC outperform state-of-the-art methods by at least 9.8\%/6.6\% and 6.4\%/6.2\% of average mAP/R@1 on two training orders.
We study lifelong learning in linear bandits, where a learner interacts with a sequence of linear bandit tasks whose parameters lie in an $m$-dimensional subspace of $\mathbb{R}^d$, thereby sharing a low-rank representation. Current literature typically assumes that the tasks are diverse, i.e., their parameters uniformly span the $m$-dimensional subspace. This assumption allows the low-rank representation to be learned before all tasks are revealed, which can be unrealistic in real-world applications. In this work, we present the first nontrivial result for sequential multi-task linear bandits without the task diversity assumption. We develop an algorithm that efficiently learns and transfers low-rank representations. When facing $N$ tasks, each played over $\tau$ rounds, our algorithm achieves a regret guarantee of $\tilde{O}\big (Nm \sqrt{\tau} + N^{\frac{2}{3}} \tau^{\frac{2}{3}} d m^{\frac13} + Nd^2 + \tau m d \big)$ under the ellipsoid action set assumption. This result can significantly improve upon the baseline of $\tilde{O} \left (Nd \sqrt{\tau}\right)$ that does not leverage the low-rank structure when the number of tasks $N$ is sufficiently large and $m \ll d$. We also demonstrate empirically on synthetic data that our algorithm outperforms baseline algorithms, which rely on the task diversity assumption.
Deep Learning for medical imaging faces challenges in adapting and generalizing to new contexts. Additionally, it often lacks sufficient labeled data for specific tasks requiring significant annotation effort. Continual Learning (CL) tackles adaptability and generalizability by enabling lifelong learning from a data stream while mitigating forgetting of previously learned knowledge. Active Learning (AL) reduces the number of required annotations for effective training. This work explores both approaches (CAL) to develop a novel framework for robust medical image analysis. Based on the automatic recognition of shifts in image characteristics, Replay-Base Architecture for Context Adaptation (RBACA) employs a CL rehearsal method to continually learn from diverse contexts, and an AL component to select the most informative instances for annotation. A novel approach to evaluate CAL methods is established using a defined metric denominated IL-Score, which allows for the simultaneous assessment of transfer learning, forgetting, and final model performance. We show that RBACA works in domain and class-incremental learning scenarios, by assessing its IL-Score on the segmentation and diagnosis of cardiac images. The results show that RBACA outperforms a baseline framework without CAL, and a state-of-the-art CAL method across various memory sizes and annotation budgets. Our code is available in https://github.com/RuiDaniel/RBACA .
Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the ability to adapt over time in response to new challenges. This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents. We categorize the core components of these agents into three modules: the perception module for multimodal input integration, the memory module for storing and retrieving evolving knowledge, and the action module for grounded interactions with the dynamic environment. We highlight how these pillars collectively enable continuous adaptation, mitigate catastrophic forgetting, and improve long-term performance. This survey provides a roadmap for researchers and practitioners working to develop lifelong learning capabilities in LLM agents, offering insights into emerging trends, evaluation metrics, and application scenarios. Relevant literature and resources are available at \href{this url}{https://github.com/qianlima-lab/awesome-lifelong-llm-agent}.
We present APT, an advanced Large Language Model (LLM)-driven framework that enables autonomous agents to construct complex and creative structures within the Minecraft environment. Unlike previous approaches that primarily concentrate on skill-based open-world tasks or rely on image-based diffusion models for generating voxel-based structures, our method leverages the intrinsic spatial reasoning capabilities of LLMs. By employing chain-of-thought decomposition along with multimodal inputs, the framework generates detailed architectural layouts and blueprints that the agent can execute under zero-shot or few-shot learning scenarios. Our agent incorporates both memory and reflection modules to facilitate lifelong learning, adaptive refinement, and error correction throughout the building process. To rigorously evaluate the agent's performance in this emerging research area, we introduce a comprehensive benchmark consisting of diverse construction tasks designed to test creativity, spatial reasoning, adherence to in-game rules, and the effective integration of multimodal instructions. Experimental results using various GPT-based LLM backends and agent configurations demonstrate the agent's capacity to accurately interpret extensive instructions involving numerous items, their positions, and orientations. The agent successfully produces complex structures complete with internal functionalities such as Redstone-powered systems. A/B testing indicates that the inclusion of a memory module leads to a significant increase in performance, emphasizing its role in enabling continuous learning and the reuse of accumulated experience. Additionally, the agent's unexpected emergence of scaffolding behavior highlights the potential of future LLM-driven agents to utilize subroutine planning and leverage the emergence ability of LLMs to autonomously develop human-like problem-solving techniques.
Lifelong prompt tuning has significantly advanced parameter-efficient lifelong learning with its efficiency and minimal storage demands on various tasks. Our empirical studies, however, highlights certain transferability constraints in the current methodologies: a universal algorithm that guarantees consistent positive transfer across all tasks is currently unattainable, especially when dealing dissimilar tasks that may engender negative transfer. Identifying the misalignment between algorithm selection and task specificity as the primary cause of negative transfer, we present the Similarity Heuristic Lifelong Prompt Tuning (SHLPT) framework. This innovative strategy partitions tasks into two distinct subsets by harnessing a learnable similarity metric, thereby facilitating fruitful transfer from tasks regardless of their similarity or dissimilarity. Additionally, SHLPT incorporates a parameter pool to combat catastrophic forgetting effectively. Our experiments shows that SHLPT outperforms state-of-the-art techniques in lifelong learning benchmarks and demonstrates robustness against negative transfer in diverse task sequences.
As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static datasets, are increasingly inadequate for coping with the dynamic nature of real-world information. Lifelong learning, also known as continual or incremental learning, addresses this challenge by enabling LLMs to learn continuously and adaptively over their operational lifetime, integrating new knowledge while retaining previously learned information and preventing catastrophic forgetting. This survey delves into the sophisticated landscape of lifelong learning, categorizing strategies into two primary groups: Internal Knowledge and External Knowledge. Internal Knowledge includes continual pretraining and continual finetuning, each enhancing the adaptability of LLMs in various scenarios. External Knowledge encompasses retrieval-based and tool-based lifelong learning, leveraging external data sources and computational tools to extend the model's capabilities without modifying core parameters. The key contributions of our survey are: (1) Introducing a novel taxonomy categorizing the extensive literature of lifelong learning into 12 scenarios; (2) Identifying common techniques across all lifelong learning scenarios and classifying existing literature into various technique groups within each scenario; (3) Highlighting emerging techniques such as model expansion and data selection, which were less explored in the pre-LLM era. Through a detailed examination of these groups and their respective categories, this survey aims to enhance the adaptability, reliability, and overall performance of LLMs in real-world applications.
Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of classification tasks, the advent of increasingly powerful generative models necessitates the exploration of Continual Learning of Generative models (CLoG). This paper advocates for shifting the research focus from classification-based CL to CLoG. We systematically identify the unique challenges presented by CLoG compared to traditional classification-based CL. We adapt three types of existing CL methodologies, replay-based, regularization-based, and parameter-isolation-based methods to generative tasks and introduce comprehensive benchmarks for CLoG that feature great diversity and broad task coverage. Our benchmarks and results yield intriguing insights that can be valuable for developing future CLoG methods. Additionally, we will release a codebase designed to facilitate easy benchmarking and experimentation in CLoG publicly at https://github.com/linhaowei1/CLoG. We believe that shifting the research focus to CLoG will benefit the continual learning community and illuminate the path for next-generation AI-generated content (AIGC) in a lifelong learning paradigm.
Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we propose a simple modification to causal language modeling called conditional finetuning, which performs language modeling conditioned on a context. We show that a context can "explain away" certain corpus statistics and make the model avoid learning them. In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases. This selective learning effect leads to less forgetting and better stability-plasticity tradeoff in domain finetuning, potentially benefitting lifelong learning with language models.
Context detection involves labeling segments of an online stream of data as belonging to different tasks. Task labels are used in lifelong learning algorithms to perform consolidation or other procedures that prevent catastrophic forgetting. Inferring task labels from online experiences remains a challenging problem. Most approaches assume finite and low-dimension observation spaces or a preliminary training phase during which task labels are learned. Moreover, changes in the transition or reward functions can be detected only in combination with a policy, and therefore are more difficult to detect than changes in the input distribution. This paper presents an approach to learning both policies and labels in an online deep reinforcement learning setting. The key idea is to use distance metrics, obtained via optimal transport methods, i.e., Wasserstein distance, on suitable latent action-reward spaces to measure distances between sets of data points from past and current streams. Such distances can then be used for statistical tests based on an adapted Kolmogorov-Smirnov calculation to assign labels to sequences of experiences. A rollback procedure is introduced to learn multiple policies by ensuring that only the appropriate data is used to train the corresponding policy. The combination of task detection and policy deployment allows for the optimization of lifelong reinforcement learning agents without an oracle that provides task labels. The approach is tested using two benchmarks and the results show promising performance when compared with related context detection algorithms. The results suggest that optimal transport statistical methods provide an explainable and justifiable procedure for online context detection and reward optimization in lifelong reinforcement learning.
Online Lifelong Learning (OLL) addresses the challenge of learning from continuous and non-stationary data streams. Existing online lifelong learning methods based on image classification models often require preset conditions such as the total number of classes or maximum memory capacity, which hinders the realization of real never-ending learning and renders them impractical for real-world scenarios. In this work, we propose that vision-language models, such as Contrastive Language-Image Pretraining (CLIP), are more suitable candidates for online lifelong learning. We discover that maintaining symmetry between image and text is crucial during Parameter-Efficient Tuning (PET) for CLIP model in online lifelong learning. To this end, we introduce the Symmetric Image-Text (SIT) tuning strategy. We conduct extensive experiments on multiple lifelong learning benchmark datasets and elucidate the effectiveness of SIT through gradient analysis. Additionally, we assess the impact of lifelong learning on generalizability of CLIP and found that tuning the image encoder is beneficial for lifelong learning, while tuning the text encoder aids in zero-shot learning.
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic forgetting. To address these issues, we propose an unsupervised CL model with task experts called Unsupervised Task Expert Lifelong Learning (U-TELL) to continually learn the data arriving in a sequence addressing catastrophic forgetting. During training of U-TELL, we introduce a new expert on arrival of a new task. Our proposed architecture has task experts, a structured data generator and a task assigner. Each task expert is composed of 3 blocks; i) a variational autoencoder to capture the task distribution and perform data abstraction, ii) a k-means clustering module, and iii) a structure extractor to preserve latent task data signature. During testing, task assigner selects a suitable expert to perform clustering. U-TELL does not store or replay task samples, instead, we use generated structured samples to train the task assigner. We compared U-TELL with five SOTA unsupervised CL methods. U-TELL outperformed all baselines on seven benchmarks and one industry dataset for various CL scenarios with a training time over 6 times faster than the best performing baseline.
In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train agents to play any Atari game. At first, this system uses advanced techniques like deep Q-networks and dueling Q-networks to train efficient agents, the same techniques used by DeepMind to train agents that beat human players in Atari games. As an extension, plastic neural networks are used as agents, and their feasibility is analyzed in this scenario. The plasticity implementation was based on backpropagation and the Hebbian update rule. Plastic neural networks have excellent features like lifelong learning after the initial training, which makes them highly suitable in adaptive learning environments. As a new analysis of plasticity in this context, this work might provide valuable insights and direction for future works.