A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms

Recommender systems (RS) have become essential in filtering information and personalizing content for users. RS techniques have traditionally relied on modeling interactions between users and items as well as the features of content using models specific to each task. The emergence of foundation models (FMs), large scale models trained on vast amounts of data such as GPT, LLaMA and CLIP, is reshaping the recommendation paradigm. This survey provides a comprehensive overview of the Foundation Models for Recommender Systems (FM4RecSys), covering their integration in three paradigms: (1) Feature-Based augmentation of representations, (2) Generative recommendation approaches, and (3) Agentic interactive systems. We first review the data foundations of RS, from traditional explicit or implicit feedback to multimodal content sources. We then introduce FMs and their capabilities for representation learning, natural language understanding, and multi-modal reasoning in RS contexts. The core of the survey discusses how FMs enhance RS under different paradigms. Afterward, we examine FM applications in various recommendation tasks. Through an analysis of recent research, we highlight key opportunities that have been realized as well as challenges encountered. Finally, we outline open research directions and technical challenges for next-generation FM4RecSys. This survey not only reviews the state-of-the-art methods but also provides a critical analysis of the trade-offs among the feature-based, the generative, and the agentic paradigms, outlining key open issues and future research directions.

In-context Ranking Preference Optimization

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such lists typically involves identifying a few relevant items in context rather than providing detailed pairwise comparisons for every possible item pair. Moreover, many complex information retrieval tasks, such as conversational agents and summarization systems, critically depend on ranking the highest-quality outputs at the top, emphasizing the need to support natural and flexible forms of user feedback. To address the challenge of limited and sparse pairwise feedback in the in-context setting, we propose an In-context Ranking Preference Optimization (IRPO) framework that directly optimizes LLMs based on ranking lists constructed during inference. To further capture flexible forms of feedback, IRPO extends the DPO objective by incorporating both the relevance of items and their positions in the list. Modeling these aspects jointly is non-trivial, as ranking metrics are inherently discrete and non-differentiable, making direct optimization difficult. To overcome this, IRPO introduces a differentiable objective based on positional aggregation of pairwise item preferences, enabling effective gradient-based optimization of discrete ranking metrics. We further provide theoretical insights showing that IRPO (i) automatically emphasizes items with greater disagreement between the model and the reference ranking, and (ii) links its gradient to an importance sampling estimator, yielding an unbiased estimator with reduced variance. Empirical results show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.

From Reviews to Dialogues: Active Synthesis for Zero-Shot LLM-based Conversational Recommender System

Conversational recommender systems (CRS) typically require extensive domain-specific conversational datasets, yet high costs, privacy concerns, and data-collection challenges severely limit their availability. Although Large Language Models (LLMs) demonstrate strong zero-shot recommendation capabilities, practical applications often favor smaller, internally managed recommender models due to scalability, interpretability, and data privacy constraints, especially in sensitive or rapidly evolving domains. However, training these smaller models effectively still demands substantial domain-specific conversational data, which remains challenging to obtain. To address these limitations, we propose an active data augmentation framework that synthesizes conversational training data by leveraging black-box LLMs guided by active learning techniques. Specifically, our method utilizes publicly available non-conversational domain data, including item metadata, user reviews, and collaborative signals, as seed inputs. By employing active learning strategies to select the most informative seed samples, our approach efficiently guides LLMs to generate synthetic, semantically coherent conversational interactions tailored explicitly to the target domain. Extensive experiments validate that conversational data generated by our proposed framework significantly improves the performance of LLM-based CRS models, effectively addressing the challenges of building CRS in no- or low-resource scenarios.

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the area of NLP and personalization. In this survey, we present an analysis of works on personalized alignment and modeling for LLMs. We introduce a taxonomy of preference alignment techniques, including training time, inference time, and additionally, user-modeling based methods. We provide analysis and discussion on the strengths and limitations of each group of techniques and then cover evaluation, benchmarks, as well as open problems in the field.

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models

Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models. By empowering LLMs to perceive external environments, integrate multimodal information, and interact with various tools, these agentic systems exhibit greater autonomy and adaptability across complex tasks. This evolution brings new opportunities to recommender systems (RS): LLM-based Agentic RS (LLM-ARS) can offer more interactive, context-aware, and proactive recommendations, potentially reshaping the user experience and broadening the application scope of RS. Despite promising early results, fundamental challenges remain, including how to effectively incorporate external knowledge, balance autonomy with controllability, and evaluate performance in dynamic, multimodal settings. In this perspective paper, we first present a systematic analysis of LLM-ARS: (1) clarifying core concepts and architectures; (2) highlighting how agentic capabilities -- such as planning, memory, and multimodal reasoning -- can enhance recommendation quality; and (3) outlining key research questions in areas such as safety, efficiency, and lifelong personalization. We also discuss open problems and future directions, arguing that LLM-ARS will drive the next wave of RS innovation. Ultimately, we foresee a paradigm shift toward intelligent, autonomous, and collaborative recommendation experiences that more closely align with users' evolving needs and complex decision-making processes.

Active Learning for Direct Preference Optimization

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of selecting the most informative feedback for training them is under-explored. We propose an active learning framework for DPO, which can be applied to collect human feedback online or to choose the most informative subset of already collected feedback offline. We propose efficient algorithms for both settings. The key idea is to linearize the DPO objective at the last layer of the neural network representation of the optimized policy and then compute the D-optimal design to collect preferential feedback. We prove that the errors in our DPO logit estimates diminish with more feedback. We show the effectiveness of our algorithms empirically in the setting that matches our theory and also on large language models.

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent

Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue, often compressing visual representations and prioritizing task alignment over visual retention, which further worsens visual forgetting. To overcome this limitation, we introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation richness, interpreting this degradation through the information bottleneck principle as excessive compression that leads to the degradation of crucial pre-trained visual knowledge. Building on this view, we propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations while mitigating the over-compression effects described by the information bottleneck. By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation. To enable lightweight instruction-tuning, we further develop a memory-efficient fine-tuning approach using gradient masking, which selectively updates a subset of model parameters to enable parameter-efficient fine-tuning (PEFT), reducing computational overhead while preserving rich visual representations. Extensive experiments across various downstream tasks and backbone MLLMs demonstrate that MDGD effectively mitigates visual forgetting from pre-trained tasks while enabling strong adaptation to new tasks.

From Selection to Generation: A Survey of LLM-based Active Learning

Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generating entirely new data instances and providing more cost-effective annotations. Motivated by the increasing importance of high-quality data and efficient model training in the era of LLMs, we present a comprehensive survey on LLM-based Active Learning. We introduce an intuitive taxonomy that categorizes these techniques and discuss the transformative roles LLMs can play in the active learning loop. We further examine the impact of AL on LLM learning paradigms and its applications across various domains. Finally, we identify open challenges and propose future research directions. This survey aims to serve as an up-to-date resource for researchers and practitioners seeking to gain an intuitive understanding of LLM-based AL techniques and deploy them to new applications.

Interactive Visualization Recommendation with Hier-SUCB

Visualization recommendation aims to enable rapid visual analysis of massive datasets. In real-world scenarios, it is essential to quickly gather and comprehend user preferences to cover users from diverse backgrounds, including varying skill levels and analytical tasks. Previous approaches to personalized visualization recommendations are non-interactive and rely on initial user data for new users. As a result, these models cannot effectively explore options or adapt to real-time feedback. To address this limitation, we propose an interactive personalized visualization recommendation (PVisRec) system that learns on user feedback from previous interactions. For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual combinatorial semi-bandit in the PVisRec setting. Theoretically, we show an improved overall regret bound with the same rank of time but an improved rank of action space. We further demonstrate the effectiveness of Hier-SUCB through extensive experiments where it is comparable to offline methods and outperforms other bandit algorithms in the setting of visualization recommendation.

GUI Agents: A Survey

Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods. We propose a unified framework that delineates their perception, reasoning, planning, and acting capabilities. Furthermore, we identify important open challenges and discuss key future directions. Finally, this work serves as a basis for practitioners and researchers to gain an intuitive understanding of current progress, techniques, benchmarks, and critical open problems that remain to be addressed.