Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two aspects: 1) Temporal inaccuracy: memories are organized by dialogue time rather than their actual occurrence time; 2) Temporal fragmentation: existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns. To address these limitations, we propose Temporal Semantic Memory (TSM), a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory. During memory construction, it first builds a semantic timeline rather than a dialogue one. Then, it consolidates temporally continuous and semantically related information into a durative memory. During memory utilization, it incorporates the query's temporal intent on the semantic timeline, enabling the retrieval of temporally appropriate durative memories and providing time-valid, duration-consistent context to support response generation. Experiments on LongMemEval and LoCoMo show that TSM consistently outperforms existing methods and achieves up to 12.2% absolute improvement in accuracy, demonstrating the effectiveness of the proposed method.

Beyond Motion Pattern: An Empirical Study of Physical Forces for Human Motion Understanding

Human motion understanding has advanced rapidly through vision-based progress in recognition, tracking, and captioning. However, most existing methods overlook physical cues such as joint actuation forces that are fundamental in biomechanics. This gap motivates our study: if and when do physically inferred forces enhance motion understanding? By incorporating forces into established motion understanding pipelines, we systematically evaluate their impact across baseline models on 3 major tasks: gait recognition, action recognition, and fine-grained video captioning. Across 8 benchmarks, incorporating forces yields consistent performance gains; for example, on CASIA-B, Rank-1 gait recognition accuracy improved from 89.52% to 90.39% (+0.87), with larger gain observed under challenging conditions: +2.7% when wearing a coat and +3.0% at the side view. On Gait3D, performance also increases from 46.0% to 47.3% (+1.3). In action recognition, CTR-GCN achieved +2.00% on Penn Action, while high-exertion classes like punching/slapping improved by +6.96%. Even in video captioning, Qwen2.5-VL's ROUGE-L score rose from 0.310 to 0.339 (+0.029), indicating that physics-inferred forces enhance temporal grounding and semantic richness. These results demonstrate that force cues can substantially complement visual and kinematic features under dynamic, occluded, or appearance-varying conditions.

SuperWing: a comprehensive transonic wing dataset for data-driven aerodynamic design

Machine-learning surrogate models have shown promise in accelerating aerodynamic design, yet progress toward generalizable predictors for three-dimensional wings has been limited by the scarcity and restricted diversity of existing datasets. Here, we present SuperWing, a comprehensive open dataset of transonic swept-wing aerodynamics comprising 4,239 parameterized wing geometries and 28,856 Reynolds-averaged Navier-Stokes flow field solutions. The wing shapes in the dataset are generated using a simplified yet expressive geometry parameterization that incorporates spanwise variations in airfoil shape, twist, and dihedral, allowing for an enhanced diversity without relying on perturbations of a baseline wing. All shapes are simulated under a broad range of Mach numbers and angles of attack covering the typical flight envelope. To demonstrate the dataset's utility, we benchmark two state-of-the-art Transformers that accurately predict surface flow and achieve a 2.5 drag-count error on held-out samples. Models pretrained on SuperWing further exhibit strong zero-shot generalization to complex benchmark wings such as DLR-F6 and NASA CRM, underscoring the dataset's diversity and potential for practical usage.

LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services

Recent advances in large reasoning models (LRMs) have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on general information retrieval and rarely explores vertical domains with unique challenges. In this work, we focus on local life services and introduce LocalSearchBench, which encompass diverse and complex business scenarios. Real-world queries in this domain are often ambiguous and require multi-hop reasoning across merchants and products, remaining challenging and not fully addressed. As the first comprehensive benchmark for agentic search in local life services, LocalSearchBench includes over 150,000 high-quality entries from various cities and business types. We construct 300 multi-hop QA tasks based on real user queries, challenging agents to understand questions and retrieve information in multiple steps. We also developed LocalPlayground, a unified environment integrating multiple tools for agent interaction. Experiments show that even state-of-the-art LRMs struggle on LocalSearchBench: the best model (DeepSeek-V3.1) achieves only 34.34% correctness, and most models have issues with completeness (average 77.33%) and faithfulness (average 61.99%). This highlights the need for specialized benchmarks and domain-specific agent training in local life services. Code, Benchmark, and Leaderboard are available at localsearchbench.github.io.

Design, Results and Industry Implications of the World's First Insurance Large Language Model Evaluation Benchmark

This paper comprehensively elaborates on the construction methodology, multi-dimensional evaluation system, and underlying design philosophy of CUFEInse v1.0. Adhering to the principles of "quantitative-oriented, expert-driven, and multi-validation," the benchmark establishes an evaluation framework covering 5 core dimensions, 54 sub-indicators, and 14,430 high-quality questions, encompassing insurance theoretical knowledge, industry understanding, safety and compliance, intelligent agent application, and logical rigor. Based on this benchmark, a comprehensive evaluation was conducted on 11 mainstream large language models. The evaluation results reveal that general-purpose models suffer from common bottlenecks such as weak actuarial capabilities and inadequate compliance adaptation. High-quality domain-specific training demonstrates significant advantages in insurance vertical scenarios but exhibits shortcomings in business adaptation and compliance. The evaluation also accurately identifies the common bottlenecks of current large models in professional scenarios such as insurance actuarial, underwriting and claim settlement reasoning, and compliant marketing copywriting. The establishment of CUFEInse not only fills the gap in professional evaluation benchmarks for the insurance field, providing academia and industry with a professional, systematic, and authoritative evaluation tool, but also its construction concept and methodology offer important references for the evaluation paradigm of large models in vertical fields, serving as an authoritative reference for academic model optimization and industrial model selection. Finally, the paper looks forward to the future iteration direction of the evaluation benchmark and the core development direction of "domain adaptation + reasoning enhancement" for insurance large models.

OneRec-V2 Technical Report

Recent breakthroughs in generative AI have transformed recommender systems through end-to-end generation. OneRec reformulates recommendation as an autoregressive generation task, achieving high Model FLOPs Utilization. While OneRec-V1 has shown significant empirical success in real-world deployment, two critical challenges hinder its scalability and performance: (1) inefficient computational allocation where 97.66% of resources are consumed by sequence encoding rather than generation, and (2) limitations in reinforcement learning relying solely on reward models. To address these challenges, we propose OneRec-V2, featuring: (1) Lazy Decoder-Only Architecture: Eliminates encoder bottlenecks, reducing total computation by 94% and training resources by 90%, enabling successful scaling to 8B parameters. (2) Preference Alignment with Real-World User Interactions: Incorporates Duration-Aware Reward Shaping and Adaptive Ratio Clipping to better align with user preferences using real-world feedback. Extensive A/B tests on Kuaishou demonstrate OneRec-V2's effectiveness, improving App Stay Time by 0.467%/0.741% while balancing multi-objective recommendations. This work advances generative recommendation scalability and alignment with real-world feedback, representing a step forward in the development of end-to-end recommender systems.

OneRec Technical Report

Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from the AI community in recommendation scenarios. To address these issues, we propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 $\times$ and have identified the scaling laws for recommendations within certain boundaries. Secondly, reinforcement learning techniques, previously difficult to apply for optimizing recommendations, show significant potential in this framework. Lastly, through infrastructure optimizations, we have achieved 23.7% and 28.8% Model FLOPs Utilization (MFU) on flagship GPUs during training and inference, respectively, aligning closely with the LLM community. This architecture significantly reduces communication and storage overhead, resulting in operating expense that is only 10.6% of traditional recommendation pipelines. Deployed in Kuaishou/Kuaishou Lite APP, it handles 25% of total queries per second, enhancing overall App Stay Time by 0.54% and 1.24%, respectively. Additionally, we have observed significant increases in metrics such as 7-day Lifetime, which is a crucial indicator of recommendation experience. We also provide practical lessons and insights derived from developing, optimizing, and maintaining a production-scale recommendation system with significant real-world impact.

Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models

Large language models (LLMs) have mastered abundant simple and explicit commonsense knowledge through pre-training, enabling them to achieve human-like performance in simple commonsense reasoning. Nevertheless, LLMs struggle to reason with complex and implicit commonsense knowledge that is derived from simple ones (such as understanding the long-term effects of certain events), an aspect humans tend to focus on more. Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure. To fill this gap and align with real-world concerns, we propose a benchmark Com$^2$ focusing on complex commonsense reasoning. We first incorporate causal event graphs to serve as structured complex commonsense. Then we adopt causal theory~(e.g., intervention) to modify the causal event graphs and obtain different scenarios that meet human concerns. Finally, an LLM is employed to synthesize examples with slow thinking, which is guided by the logical relationships in the modified causal graphs. Furthermore, we use detective stories to construct a more challenging subset. Experiments show that LLMs struggle in reasoning depth and breadth, while post-training and slow thinking can alleviate this. The code and data are available at https://github.com/Waste-Wood/Com2.

Hi-LSplat: Hierarchical 3D Language Gaussian Splatting

Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a unified 3D representation, leading to view inconsistencies. Additionally, inherent open-vocabulary challenges cause inconsistencies in object and relational descriptions, impeding hierarchical semantic understanding. In this paper, we propose Hi-LSplat, a view-consistent Hierarchical Language Gaussian Splatting work for 3D open-vocabulary querying. To achieve view-consistent 3D hierarchical semantics, we first lift 2D features to 3D features by constructing a 3D hierarchical semantic tree with layered instance clustering, which addresses the view inconsistency issue caused by 2D semantic features. Besides, we introduce instance-wise and part-wise contrastive losses to capture all-sided hierarchical semantic representations. Notably, we construct two hierarchical semantic datasets to better assess the model's ability to distinguish different semantic levels. Extensive experiments highlight our method's superiority in 3D open-vocabulary segmentation and localization. Its strong performance on hierarchical semantic datasets underscores its ability to capture complex hierarchical semantics within 3D scenes.

Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games

Multi-agent reinforcement learning, despite its popularity and empirical success, faces significant scalability challenges in large-population dynamic games. Graphon mean field games (GMFGs) offer a principled framework for approximating such games while capturing heterogeneity among players. In this paper, we propose and analyze a policy optimization framework for continuous-time, finite-horizon linear-quadratic GMFGs. Exploiting the structural properties of GMFGs, we design an efficient policy parameterization in which each player's policy is represented as an affine function of their private state, with a shared slope function and player-specific intercepts. We develop a bilevel optimization algorithm that alternates between policy gradient updates for best-response computation under a fixed population distribution, and distribution updates using the resulting policies. We prove linear convergence of the policy gradient steps to best-response policies and establish global convergence of the overall algorithm to the Nash equilibrium. The analysis relies on novel landscape characterizations over infinite-dimensional policy spaces. Numerical experiments demonstrate the convergence and robustness of the proposed algorithm under varying graphon structures, noise levels, and action frequencies.