MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation

The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both industry and academia. However, the advent of large-scale recommenders also brings significantly higher computational costs, particularly under the long-sequence dependencies inherent in the user intent of recommendation systems. Current approaches often rely on pre-storing the intermediate states of the past behavior for each user, thereby reducing the quadratic re-computation cost for the following requests. Despite their effectiveness, these methods often treat memory merely as a medium for acceleration, without adequately considering the space overhead it introduces. This presents a critical challenge in real-world recommendation systems with billions of users, each of whom might initiate thousands of interactions and require massive memory for state storage. Fortunately, there have been several memory management strategies examined for compression in LLM, while most have not been evaluated on the recommendation task. To mitigate this gap, we introduce MALLOC, a comprehensive benchmark for memory-aware long sequence compression. MALLOC presents a comprehensive investigation and systematic classification of memory management techniques applicable to large sequential recommendations. These techniques are integrated into state-of-the-art recommenders, enabling a reproducible and accessible evaluation platform. Through extensive experiments across accuracy, efficiency, and complexity, we demonstrate the holistic reliability of MALLOC in advancing large-scale recommendation. Code is available at https://anonymous.4open.science/r/MALLOC.

Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction

User behavior sequences in modern recommendation systems exhibit significant length heterogeneity, ranging from sparse short-term interactions to rich long-term histories. While longer sequences provide more context, we observe that increasing the maximum input sequence length in existing CTR models paradoxically degrades performance for short-sequence users due to attention polarization and length imbalance in training data. To address this, we propose LAIN(Length-Adaptive Interest Network), a plug-and-play framework that explicitly incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling. LAIN consists of three lightweight components: a Spectral Length Encoder that maps length into continuous representations, Length-Conditioned Prompting that injects global contextual cues into both long- and short-term behavior branches, and Length-Modulated Attention that adaptively adjusts attention sharpness based on sequence length. Extensive experiments on three real-world benchmarks across five strong CTR backbones show that LAIN consistently improves overall performance, achieving up to 1.15% AUC gain and 2.25% log loss reduction. Notably, our method significantly improves accuracy for short-sequence users without sacrificing longsequence effectiveness. Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on integer quantization, while their applicability and behavior under MXFP formats remain largely unexplored. To address this gap, this work conducts a systematic investigation of PTQ under MXFP formats, encompassing over 7 PTQ algorithms, 15 evaluation benchmarks, and 3 LLM families. The key findings include: 1) MXFP8 consistently achieves near-lossless performance, while MXFP4 introduces substantial accuracy degradation and remains challenging; 2) PTQ effectiveness under MXFP depends strongly on format compatibility, with some algorithmic paradigms being consistently more effective than others; 3) PTQ performance exhibits highly consistent trends across model families and modalities, in particular, quantization sensitivity is dominated by the language model rather than the vision encoder in multimodal LLMs; 4) The scaling factor of quantization is a critical error source in MXFP4, and a simple pre-scale optimization strategy can significantly mitigate its impact. Together, these results provide practical guidance on adapting existing PTQ methods to MXFP quantization.

SwiftMem: Fast Agentic Memory via Query-aware Indexing

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform exhaustive retrieval across the entire storage layer regardless of query characteristics. This brute-force approach creates severe latency bottlenecks as memory grows, hindering real-time agent interactions. We propose SwiftMem, a query-aware agentic memory system that achieves sub-linear retrieval through specialized indexing over temporal and semantic dimensions. Our temporal index enables logarithmic-time range queries for time-sensitive retrieval, while the semantic DAG-Tag index maps queries to relevant topics through hierarchical tag structures. To address memory fragmentation during growth, we introduce an embedding-tag co-consolidation mechanism that reorganizes storage based on semantic clusters to improve cache locality. Experiments on LoCoMo and LongMemEval benchmarks demonstrate that SwiftMem achieves 47$\times$ faster search compared to state-of-the-art baselines while maintaining competitive accuracy, enabling practical deployment of memory-augmented LLM agents.

What Matters For Safety Alignment?

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

Towards Efficient Agents: A Co-Design of Inference Architecture and System

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe inefficiencies that arise not from isolated model inference, but from the systemic latency accumulated across reasoning loops, context growth, and heterogeneous tool interactions. This paper presents AgentInfer, a unified framework for end-to-end agent acceleration that bridges inference optimization and architectural design. We decompose the problem into four synergistic components: AgentCollab, a hierarchical dual-model reasoning framework that balances large- and small-model usage through dynamic role assignment; AgentSched, a cache-aware hybrid scheduler that minimizes latency under heterogeneous request patterns; AgentSAM, a suffix-automaton-based speculative decoding method that reuses multi-session semantic memory to achieve low-overhead inference acceleration; and AgentCompress, a semantic compression mechanism that asynchronously distills and reorganizes agent memory without disrupting ongoing reasoning. Together, these modules form a Self-Evolution Engine capable of sustaining efficiency and cognitive stability throughout long-horizon reasoning tasks. Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%, achieving an overall 1.8-2.5 times speedup with preserved accuracy. These results underscore that optimizing for agentic task completion-rather than merely per-token throughput-is the key to building scalable, efficient, and self-improving intelligent systems.

FAIR: Focused Attention Is All You Need for Generative Recommendation

Recently, transformer-based generative recommendation has garnered significant attention for user behavior modeling. However, it often requires discretizing items into multi-code representations (e.g., typically four code tokens or more), which sharply increases the length of the original item sequence. This expansion poses challenges to transformer-based models for modeling user behavior sequences with inherent noises, since they tend to overallocate attention to irrelevant or noisy context. To mitigate this issue, we propose FAIR, the first generative recommendation framework with focused attention, which enhances attention scores to relevant context while suppressing those to irrelevant ones. Specifically, we propose (1) a focused attention mechanism integrated into the standard Transformer, which learns two separate sets of Q and K attention weights and computes their difference as the final attention scores to eliminate attention noise while focusing on relevant contexts; (2) a noise-robustness objective, which encourages the model to maintain stable attention patterns under stochastic perturbations, preventing undesirable shifts toward irrelevant context due to noise; and (3) a mutual information maximization objective, which guides the model to identify contexts that are most informative for next-item prediction. We validate the effectiveness of FAIR on four public benchmarks, demonstrating its superior performance compared to existing methods.

FuXi-$γ$: Efficient Sequential Recommendation with Exponential-Power Temporal Encoder and Diagonal-Sparse Positional Mechanism

Sequential recommendation aims to model users' evolving preferences based on their historical interactions. Recent advances leverage Transformer-based architectures to capture global dependencies, but existing methods often suffer from high computational overhead, primarily due to discontinuous memory access in temporal encoding and dense attention over long sequences. To address these limitations, we propose FuXi-$γ$, a novel sequential recommendation framework that improves both effectiveness and efficiency through principled architectural design. FuXi-$γ$ adopts a decoder-only Transformer structure and introduces two key innovations: (1) An exponential-power temporal encoder that encodes relative temporal intervals using a tunable exponential decay function inspired by the Ebbinghaus forgetting curve. This encoder enables flexible modeling of both short-term and long-term preferences while maintaining high efficiency through continuous memory access and pure matrix operations. (2) A diagonal-sparse positional mechanism that prunes low-contribution attention blocks using a diagonal-sliding strategy guided by the persymmetry of Toeplitz matrix. Extensive experiments on four real-world datasets demonstrate that FuXi-$γ$ achieves state-of-the-art performance in recommendation quality, while accelerating training by up to 4.74$\times$ and inference by up to 6.18$\times$, making it a practical and scalable solution for long-sequence recommendation. Our code is available at https://github.com/Yeedzhi/FuXi-gamma.

Think Socially via Cognitive Reasoning

LLMs trained for logical reasoning excel at step-by-step deduction to reach verifiable answers. However, this paradigm is ill-suited for navigating social situations, which induce an interpretive process of analyzing ambiguous cues that rarely yield a definitive outcome. To bridge this gap, we introduce Cognitive Reasoning, a paradigm modeled on human social cognition. It formulates the interpretive process into a structured cognitive flow of interconnected cognitive units (e.g., observation or attribution), which combine adaptively to enable effective social thinking and responses. We then propose CogFlow, a complete framework that instills this capability in LLMs. CogFlow first curates a dataset of cognitive flows by simulating the associative and progressive nature of human thought via tree-structured planning. After instilling the basic cognitive reasoning capability via supervised fine-tuning, CogFlow adopts reinforcement learning to enable the model to improve itself via trial and error, guided by a multi-objective reward that optimizes both cognitive flow and response quality. Extensive experiments show that CogFlow effectively enhances the social cognitive capabilities of LLMs, and even humans, leading to more effective social decision-making.

Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent

Recent advancements in Large Language Models (LLMs) have significantly propelled the development of Conversational Recommendation Agents (CRAs). However, these agents often generate short-sighted responses that fail to sustain user guidance and meet expectations. Although preference optimization has proven effective in aligning LLMs with user expectations, it remains costly and performs poorly in multi-turn dialogue. To address this challenge, we introduce a novel multi-turn preference optimization (MTPO) paradigm ECPO, which leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turn dialogues, uncovering the underlying causes of dissatisfaction. These causes can be utilized to support targeted optimization of unsatisfactory responses, thereby achieving turn-level preference optimization. ECPO ingeniously eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements. To support ECPO, we introduce an LLM-based user simulator, AILO, to simulate user feedback and perform expectation confirmation during conversational recommendations. Experimental results show that ECPO significantly enhances CRA's interaction capabilities, delivering notable improvements in both efficiency and effectiveness over existing MTPO methods.