Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design

Real-time generative game engines represent a paradigm shift in interactive simulation, promising to replace traditional graphics pipelines with neural world models. However, existing approaches are fundamentally constrained by the ``Memory Wall,'' restricting practical deployments to low resolutions (e.g., $64 \times 64$). This paper bridges the gap between generative models and high-resolution neural simulations by introducing a scalable \textit{Hardware-Algorithm Co-Design} framework. We identify that high-resolution generation suffers from a critical resource mismatch: the World Model is compute-bound while the Decoder is memory-bound. To address this, we propose a heterogeneous architecture that intelligently decouples these components across a cluster of AI accelerators. Our system features three core innovations: (1) an asymmetric resource allocation strategy that optimizes throughput under sequence parallelism constraints; (2) a memory-centric operator fusion scheme that minimizes off-chip bandwidth usage; and (3) a manifold-aware latent extrapolation mechanism that exploits temporal redundancy to mask latency. We validate our approach on a cluster of programmable AI accelerators, enabling real-time generation at $720 \times 480$ resolution -- a $50\times$ increase in pixel throughput over prior baselines. Evaluated on both continuous 3D racing and discrete 2D platformer benchmarks, our system delivers fluid 26.4 FPS and 48.3 FPS respectively, with an amortized effective latency of 2.7 ms. This work demonstrates that resolving the ``Memory Wall'' via architectural co-design is not merely an optimization, but a prerequisite for enabling high-fidelity, responsive neural gameplay.

Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis

Multimodal large language models (MLLMs) have shown remarkable capabilities, yet their performance is often capped by the coarse nature of existing alignment techniques. A critical bottleneck remains the lack of effective reward models (RMs): existing RMs are predominantly vision-centric, return opaque scalar scores, and rely on costly human annotations. We introduce \textbf{Omni-RRM}, the first open-source rubric-grounded reward model that produces structured, multi-dimension preference judgments with dimension-wise justifications across \textbf{text, image, video, and audio}. At the core of our approach is \textbf{Omni-Preference}, a large-scale dataset built via a fully automated pipeline: we synthesize candidate response pairs by contrasting models of different capabilities, and use strong teacher models to \emph{reconcile and filter} preferences while providing a modality-aware \emph{rubric-grounded rationale} for each pair. This eliminates the need for human-labeled training preferences. Omni-RRM is trained in two stages: supervised fine-tuning to learn the rubric-grounded outputs, followed by reinforcement learning (GRPO) to sharpen discrimination on difficult, low-contrast pairs. Comprehensive evaluations show that Omni-RRM achieves state-of-the-art accuracy on video (80.2\% on ShareGPT-V) and audio (66.8\% on Audio-HH-RLHF) benchmarks, and substantially outperforms existing open-source RMs on image tasks, with a 17.7\% absolute gain over its base model on overall accuracy. Omni-RRM also improves downstream performance via Best-of-$N$ selection and transfers to text-only preference benchmarks. Our data, code, and models are available at https://anonymous.4open.science/r/Omni-RRM-CC08.

MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux

Graphical user interface (GUI) agents are rapidly progressing toward autonomous interaction and reliable task execution across diverse applications. However, two central challenges remain unresolved: automating the evaluation of agent trajectories and generating high-quality training data at scale to enable continual improvement. Existing approaches often depend on manual annotation or static rule-based verification, which restricts scalability and limits adaptability in dynamic environments. We present MagicGUI-RMS, a multi-agent reward model system that delivers adaptive trajectory evaluation, corrective feedback, and self-evolving learning capabilities. MagicGUI-RMS integrates a Domain-Specific Reward Model (DS-RM) with a General-Purpose Reward Model (GP-RM), enabling fine-grained action assessment and robust generalization across heterogeneous GUI tasks. To support reward learning at scale, we design a structured data construction pipeline that automatically produces balanced and diverse reward datasets, effectively reducing annotation costs while maintaining sample fidelity. During execution, the reward model system identifies erroneous actions, proposes refined alternatives, and continuously enhances agent behavior through an automated data-reflux mechanism. Extensive experiments demonstrate that MagicGUI-RMS yields substantial gains in task accuracy, behavioral robustness. These results establish MagicGUI-RMS as a principled and effective foundation for building self-improving GUI agents driven by reward-based adaptation.

Beyond Accuracy: Evaluating Grounded Visual Evidence in Thinking with Images

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly rely on outcome-oriented accuracy, lacking the capability to assess whether models can accurately leverage fine-grained visual cues for multi-step reasoning. To address these limitations, we propose ViEBench, a process-verifiable benchmark designed to evaluate faithful visual reasoning. Comprising 200 multi-scenario high-resolution images with expert-annotated visual evidence, ViEBench uniquely categorizes tasks by difficulty into perception and reasoning dimensions, where reasoning tasks require utilizing localized visual details with prior knowledge. To establish comprehensive evaluation criteria, we introduce a dual-axis matrix that provides fine-grained metrics through four diagnostic quadrants, enabling transparent diagnosis of model behavior across varying task complexities. Our experiments yield several interesting observations: (1) VLMs can sometimes produce correct final answers despite grounding on irrelevant regions, and (2) they may successfully locate the correct evidence but still fail to utilize it to reach accurate conclusions. Our findings demonstrate that ViEBench can serve as a more explainable and practical benchmark for comprehensively evaluating the effectiveness agentic VLMs. The codes will be released at: https://github.com/Xuchen-Li/ViEBench.

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. This paper proposes the Meta-Cognitive Memory Abstraction method (MCMA), which treats memory abstraction as a learnable cognitive skill rather than a fixed design choice. MCMA decouples task execution from memory management by combining a frozen task model with a learned memory copilot. The memory copilot is trained using direct preference optimization, it determines how memories should be structured, abstracted, and reused. Memories are further organized into a hierarchy of abstraction levels, enabling selective reuse based on task similarity. When no memory is transferable, MCMA transfers the ability to abstract and manage memory by transferring the memory copilot. Experiments on ALFWorld, ScienceWorld, and BabyAI demonstrate substantial improvements in performance, out-of-distribution generalization, and cross-task transfer over several baselines.

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.

Mask-Guided Multi-Task Network for Face Attribute Recognition

Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognition methods often process the entire feature map for feature extraction and attribute classification, which can produce redundant features due to reliance on global regions. To address these challenges, we propose a novel approach emphasizing the selection of specific feature regions for efficient feature learning. We introduce the Mask-Guided Multi-Task Network (MGMTN), which integrates Adaptive Mask Learning (AML) and Group-Global Feature Fusion (G2FF) to address the aforementioned limitations. Leveraging a pre-trained keypoint annotation model and a fully convolutional network, AML accurately localizes critical facial parts (e.g., eye and mouth groups) and generates group masks that delineate meaningful feature regions, thereby mitigating negative transfer from global region usage. Furthermore, G2FF combines group and global features to enhance FAR learning, enabling more precise attribute identification. Extensive experiments on two challenging facial attribute recognition datasets demonstrate the effectiveness of MGMTN in improving FAR performance.

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outperforming PEFT on several tasks. However, ReFT exhibits a significant performance decline on mathematical reasoning tasks. To address this problem, the paper demonstrates that ReFT's poor performance on mathematical tasks primarily stems from its struggle to generate effective reasoning prefixes during the early inference phase. Moreover, ReFT disturbs the numerical encoding and the error accumulats during the CoT stage. Based on these observations, this paper proposes Bias-REstrained Prefix Representation FineTuning (BREP ReFT), which enhances ReFT's mathematical reasoning capability by truncating training data to optimize the generation of initial reasoning prefixes, intervening on the early inference stage to prevent error accumulation, and constraining the intervention vectors' magnitude to avoid disturbing numerical encoding. Extensive experiments across diverse model architectures demonstrate BREP's superior effectiveness, efficiency, and robust generalization capability, outperforming both standard ReFT and weight-based PEFT methods on the task of mathematical reasoning. The source code is available at https://github.com/LiangThree/BREP.

NoteEx: Interactive Visual Context Manipulation for LLM-Assisted Exploratory Data Analysis in Computational Notebooks

Computational notebooks have become popular for Exploratory Data Analysis (EDA), augmented by LLM-based code generation and result interpretation. Effective LLM assistance hinges on selecting informative context -- the minimal set of cells whose code, data, or outputs suffice to answer a prompt. As notebooks grow long and messy, users can lose track of the mental model of their analysis. They thus fail to curate appropriate contexts for LLM tasks, causing frustration and tedious prompt engineering. We conducted a formative study (n=6) that surfaced challenges in LLM context selection and mental model maintenance. Therefore, we introduce NoteEx, a JupyterLab extension that provides a semantic visualization of the EDA workflow, allowing analysts to externalize their mental model, specify analysis dependencies, and enable interactive selection of task-relevant contexts for LLMs. A user study (n=12) against a baseline shows that NoteEx improved mental model retention and context selection, leading to more accurate and relevant LLM responses.

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database to detect anomalies and generate reports following an operating manual. However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversity, realism, and long-horizon complexity required to evaluate agents' real-world performance. To address this gap, we introduce the Tool Decathlon (dubbed as Toolathlon), a benchmark for language agents offering diverse Apps and tools, realistic environment setup, and reliable execution-based evaluation. Toolathlon spans 32 software applications and 604 tools, ranging from everyday platforms such as Google Calendar and Notion to professional ones like WooCommerce, Kubernetes, and BigQuery. Most of the tools are based on a high-quality set of Model Context Protocol (MCP) servers that we may have revised or implemented ourselves. Unlike prior works, which primarily ensure functional realism but offer limited environment state diversity, we provide realistic initial environment states from real software, such as Canvas courses with dozens of students or real financial spreadsheets. This benchmark includes 108 manually sourced or crafted tasks in total, requiring interacting with multiple Apps over around 20 turns on average to complete. Each task is strictly verifiable through dedicated evaluation scripts. Comprehensive evaluation of SOTA models highlights their significant shortcomings: the best-performing model, Claude-4.5-Sonnet, achieves only a 38.6% success rate with 20.2 tool calling turns on average, while the top open-weights model DeepSeek-V3.2-Exp reaches 20.1%. We expect Toolathlon to drive the development of more capable language agents for real-world, long-horizon task execution.