FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning

Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand. Recent advances in reinforcement-learning-based post-training have unlocked strong instruction-following and reasoning capabilities in LLMs, suggesting a principled route for aligning them to complex recommendation goals. Motivated by this, we study closed-set autoregressive ranking, where an LLM generates a permutation over a fixed candidate set conditioned on user context and an explicit need instruction. However, applying RL to this setting faces two key obstacles: (i) sequence-level rewards yield coarse credit assignment that fails to provide fine-grained training signals, and (ii) interaction feedback is sparse and noisy, which together lead to inefficient and unstable updates. We propose FlexRec, a post-training RL framework that addresses both issues with (1) a causally grounded item-level reward based on counterfactual swaps within the remaining candidate pool, and (2) critic-guided, uncertainty-aware scaling that explicitly models reward uncertainty and down-weights low-confidence rewards to stabilize learning under sparse supervision. Across diverse recommendation scenarios and objectives, FlexRec achieves substantial gains: it improves NDCG@5 by up to \textbf{59\%} and Recall@5 by up to \textbf{109.4\%} in need-specific ranking, and further achieves up to \textbf{24.1\%} Recall@5 improvement under generalization settings, outperforming strong traditional recommenders and LLM-based baselines.

Plain Transformers are Surprisingly Powerful Link Predictors

Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural heuristics or memory-intensive node embeddings -- approaches that struggle to generalize or scale to massive graphs. Emerging Graph Transformers (GTs) offer a potential alternative but often incur significant overhead due to complex structural encodings, hindering their applications to large-scale link prediction. We challenge these sophisticated paradigms with PENCIL, an encoder-only plain Transformer that replaces hand-crafted priors with attention over sampled local subgraphs, retaining the scalability and hardware efficiency of standard Transformers. Through experimental and theoretical analysis, we show that PENCIL extracts richer structural signals than GNNs, implicitly generalizing a broad class of heuristics and subgraph-based expressivity. Empirically, PENCIL outperforms heuristic-informed GNNs and is far more parameter-efficient than ID-embedding--based alternatives, while remaining competitive across diverse benchmarks -- even without node features. Our results challenge the prevailing reliance on complex engineering techniques, demonstrating that simple design choices are potentially sufficient to achieve the same capabilities.

Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling

Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass disperses as sequence lengths increase. We tackle these problems with Threshold Differential Attention (TDA), a sink-free attention mechanism that achieves ultra-sparsity and improved robustness at longer sequence lengths without the computational overhead of projection methods or the performance degradation caused by noise accumulation of standard rectified attention. TDA applies row-wise extreme-value thresholding with a length-dependent gate, retaining only exceedances. Inspired by the differential transformer, TDA also subtracts an inhibitory view to enhance expressivity. Theoretically, we prove that TDA controls the expected number of spurious survivors per row to $O(1)$ and that consensus spurious matches across independent views vanish as context grows. Empirically, TDA produces $>99\%$ exact zeros and eliminates attention sinks while maintaining competitive performance on standard and long-context benchmarks.

MemRec: Collaborative Memory-Augmented Agentic Recommender System

The evolution of recommender systems has shifted preference storage from rating matrices and dense embeddings to semantic memory in the agentic era. Yet existing agents rely on isolated memory, overlooking crucial collaborative signals. Bridging this gap is hindered by the dual challenges of distilling vast graph contexts without overwhelming reasoning agents with cognitive load, and evolving the collaborative memory efficiently without incurring prohibitive computational costs. To address this, we propose MemRec, a framework that architecturally decouples reasoning from memory management to enable efficient collaborative augmentation. MemRec introduces a dedicated, cost-effective LM_Mem to manage a dynamic collaborative memory graph, serving synthesized, high-signal context to a downstream LLM_Rec. The framework operates via a practical pipeline featuring efficient retrieval and cost-effective asynchronous graph propagation that evolves memory in the background. Extensive experiments on four benchmarks demonstrate that MemRec achieves state-of-the-art performance. Furthermore, architectural analysis confirms its flexibility, establishing a new Pareto frontier that balances reasoning quality, cost, and privacy through support for diverse deployments, including local open-source models. Code:https://github.com/rutgerswiselab/memrec and Homepage: https://memrec.weixinchen.com

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation

Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by prepending a single summary token, they over-compress information, hence harming performance on long documents. We propose Hierarchical Token Prepending (HTP), a method that resolves two critical bottlenecks. To mitigate attention-level compression, HTP partitions the input into blocks and prepends block-level summary tokens to subsequent blocks, creating multiple pathways for backward information flow. To address readout-level over-squashing, we replace last-token pooling with mean-pooling, a choice supported by theoretical analysis. HTP achieves consistent performance gains across 11 retrieval datasets and 30 general embedding benchmarks, especially in long-context settings. As a simple, architecture-agnostic method, HTP enhances both zero-shot and finetuned models, offering a scalable route to superior long-document embeddings.

Generative Recommendation with Semantic IDs: A Practitioner's Handbook

Generative recommendation (GR) has gained increasing attention for its promising performance compared to traditional models. A key factor contributing to the success of GR is the semantic ID (SID), which converts continuous semantic representations (e.g., from large language models) into discrete ID sequences. This enables GR models with SIDs to both incorporate semantic information and learn collaborative filtering signals, while retaining the benefits of discrete decoding. However, varied modeling techniques, hyper-parameters, and experimental setups in existing literature make direct comparisons between GR proposals challenging. Furthermore, the absence of an open-source, unified framework hinders systematic benchmarking and extension, slowing model iteration. To address this challenge, our work introduces and open-sources a framework for Generative Recommendation with semantic ID, namely GRID, specifically designed for modularity to facilitate easy component swapping and accelerate idea iteration. Using GRID, we systematically experiment with and ablate different components of GR models with SIDs on public benchmarks. Our comprehensive experiments with GRID reveal that many overlooked architectural components in GR models with SIDs substantially impact performance. This offers both novel insights and validates the utility of an open-source platform for robust benchmarking and GR research advancement. GRID is open-sourced at https://github.com/snap-research/GRID.

Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning

Backward compatible representation learning enables updated models to integrate seamlessly with existing ones, avoiding to reprocess stored data. Despite recent advances, existing compatibility approaches in Euclidean space neglect the uncertainty in the old embedding model and force the new model to reconstruct outdated representations regardless of their quality, thereby hindering the learning process of the new model. In this paper, we propose to switch perspectives to hyperbolic geometry, where we treat time as a natural axis for capturing a model's confidence and evolution. By lifting embeddings into hyperbolic space and constraining updated embeddings to lie within the entailment cone of the old ones, we maintain generational consistency across models while accounting for uncertainties in the representations. To further enhance compatibility, we introduce a robust contrastive alignment loss that dynamically adjusts alignment weights based on the uncertainty of the old embeddings. Experiments validate the superiority of the proposed method in achieving compatibility, paving the way for more resilient and adaptable machine learning systems.

Revisiting Self-attention for Cross-domain Sequential Recommendation

Sequential recommendation is a popular paradigm in modern recommender systems. In particular, one challenging problem in this space is cross-domain sequential recommendation (CDSR), which aims to predict future behaviors given user interactions across multiple domains. Existing CDSR frameworks are mostly built on the self-attention transformer and seek to improve by explicitly injecting additional domain-specific components (e.g. domain-aware module blocks). While these additional components help, we argue they overlook the core self-attention module already present in the transformer, a naturally powerful tool to learn correlations among behaviors. In this work, we aim to improve the CDSR performance for simple models from a novel perspective of enhancing the self-attention. Specifically, we introduce a Pareto-optimal self-attention and formulate the cross-domain learning as a multi-objective problem, where we optimize the recommendation task while dynamically minimizing the cross-domain attention scores. Our approach automates knowledge transfer in CDSR (dubbed as AutoCDSR) -- it not only mitigates negative transfer but also encourages complementary knowledge exchange among auxiliary domains. Based on the idea, we further introduce AutoCDSR+, a more performant variant with slight additional cost. Our proposal is easy to implement and works as a plug-and-play module that can be incorporated into existing transformer-based recommenders. Besides flexibility, it is practical to deploy because it brings little extra computational overheads without heavy hyper-parameter tuning. AutoCDSR on average improves Recall@10 for SASRec and Bert4Rec by 9.8% and 16.0% and NDCG@10 by 12.0% and 16.7%, respectively. Code is available at https://github.com/snap-research/AutoCDSR.

On the Role of Weight Decay in Collaborative Filtering: A Popularity Perspective

Collaborative filtering (CF) enables large-scale recommendation systems by encoding information from historical user-item interactions into dense ID-embedding tables. However, as embedding tables grow, closed-form solutions become impractical, often necessitating the use of mini-batch gradient descent for training. Despite extensive work on designing loss functions to train CF models, we argue that one core component of these pipelines is heavily overlooked: weight decay. Attaining high-performing models typically requires careful tuning of weight decay, regardless of loss, yet its necessity is not well understood. In this work, we question why weight decay is crucial in CF pipelines and how it impacts training. Through theoretical and empirical analysis, we surprisingly uncover that weight decay's primary function is to encode popularity information into the magnitudes of the embedding vectors. Moreover, we find that tuning weight decay acts as a coarse, non-linear knob to influence preference towards popular or unpopular items. Based on these findings, we propose PRISM (Popularity-awaRe Initialization Strategy for embedding Magnitudes), a straightforward yet effective solution to simplify the training of high-performing CF models. PRISM pre-encodes the popularity information typically learned through weight decay, eliminating its necessity. Our experiments show that PRISM improves performance by up to 4.77% and reduces training times by 38.48%, compared to state-of-the-art training strategies. Additionally, we parameterize PRISM to modulate the initialization strength, offering a cost-effective and meaningful strategy to mitigate popularity bias.