Searcharxiv⌕ Search

arXiv subjects

Meng Cao

Publications and source records attributed to Meng Cao.

At least 19 recordsLinked to original sources
arXiv2026

Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents

Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon exploration and rarely test whether agents can sustain long, dependency-heavy research processes. We introduce Mr.LHDR (Multimodal real-world Long-Horizon Deep Research), a benchmark for evaluating real-world deep research over long, irreducible chains of interdependent evidence across eight categories. Each question is constructed from a hidden Node-Relation graph and requires an average of 12.1 necessary intermediate conclusions with a mean dependency depth of 10.4 before reaching a short, unique, and verifiable answer. Questions incorporate multimodal evidence, including images, maps, PDFs, logos, charts, tables, and video frames, with at least one non-text element that changes the reasoning state. Mr.LHDR evaluates both final answers and the correctness of intermediate conclusions under annotated dependencies. We evaluate general models, deep research systems, and agent frameworks using Overall Accuracy (OA), Strict Accuracy (SA), Checklist Score (CS), and Dependency-Aware Checklist Score (DACS). Results show that even the strongest system achieves only 43.1% OA and 34.3% SA, indicating that final-answer accuracy substantially overestimates complete research success. Removing images reduces DACS by 12.6 points, demonstrating the importance of multimodal evidence, while SA consistently declines as reasoning chains become longer. These findings reveal sustained, dependency-consistent evidence integration, rather than isolated fact retrieval, as a key bottleneck for current deep research agents.

cs.AI↗
arXiv2026

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering

Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the ``one-to-many'' nature of video description, where high-quality captions are often penalized for lexical mismatches or valid shifts in visual focus. Furthermore, such assessments are typically one-dimensional, failing to provide a fine-grained analysis of caption quality. To address this, we redefine caption quality through the lens of information fidelity: A caption must maximize the coverage of salient visual information while ensuring strict factuality. We introduce CapQuiz, a novel reference-free benchmark that assesses captions based on their utility in answering human-verified, fine-grained, multiple-choice questions derived from the video. CapQuiz features a hierarchical taxonomy of 10 question types (spanning Descriptive and Inferential categories) across 24 diverse video domains. Extensive experiments demonstrate that CapQuiz correlates significantly better with human judgments than existing metrics and offers interpretable insights into model performance.

cs.CV↗
arXiv2026

WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression

Generative world models provide robots with predictive models of how the world evolves under interaction, with growing potential for simulation, planning, policy evaluation, and robot learning. Beyond clip-level future prediction, a unified generative formulation should relate actions to consequences, support flexible horizons and continuous interaction, and enable reward-driven optimization. We introduce WALL-SS, a world model that generates visual futures through Scale-wise autoregressive Scaling, enabling action-controllable and long-horizon robotic simulation. WALL-SS represents embodied trajectories as causal sequences of temporally interleaved observations and actions, making action-dependent state transitions explicit while naturally supporting variable-length generation, streaming extension through reusable causal states, and direct optimization through sequence probabilities. To make this formulation effective over long horizons, we generate each future observation in a coarse-to-fine manner and develop three complementary components within the same hierarchy. Action-conditioned next-scale prediction injects scale-aligned action representations to improve action-future coupling and model both successful and failed behaviors. Scale-compressed long-horizon memory retains recent interactions at fine resolution while compressing distant observations and actions, with scale-wise dream forcing enhancing robustness to self-generated context. Finally, on-policy alignment optimizes autoregressive visual dynamics with action-following and long-term consistency rewards while preserving the pretrained visual distribution. Experiments show that WALL-SS improves action following and trajectory accuracy, supports coherent minute-long streaming rollout under bounded memory, and consistently benefits from on-policy alignment in reducing action drift and long-horizon inconsistency.

cs.RO↗
arXiv2026

High-Quality Exposure Correction with Diffusion-Based Image Generation Priors

Although most existing exposure correction methods achieve high fidelity, they often place excessive focus on overall pixel-wise accuracy, making it challenging to effectively model extreme exposure regions, which results in suboptimal perceptual quality. Recently, diffusion models have received significant attention due to their remarkable performance in the realm of image generation. However, their successful application to exposure correction remains a challenging and open question. The key challenge lies in generating accurate image structures and maintaining high image fidelity during stochastic diffusion processes. In this paper, we propose DPEC (Diffusion Prior-based Exposure Correction), a novel framework for image exposure correction that utilizes diffusion-based image generation priors encapsulated in pre-trained large-scale diffusion models. Specifically, we first propose an efficient fine-tuning strategy to derive an exposure corrector from pre-trained models, enabling the generation of enhanced images in a single-step denoising process. Moreover, we seamlessly combine the strengths of diffusion models and regression models, and design a joint cross-attention module to integrate multi-scale diffusion prior features, thereby effectively preserving high-frequency details and minimizing random artifacts. The diffusion model focuses on dealing with low-frequency content rather than all the intricate texture details. The experimental results demonstrate that the proposed DPEC method consistently outperforms existing state-of-the-art methods on multiple exposure correction datasets, whether in terms of fidelity, perceptual quality, or visual effects.

cs.CV↗
arXiv2026

Learning with a Single Rollout via Monte Carlo Pass@k Critic

Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive. The difficulty intensifies for baseline advantage estimation methods, where repeated sampling causes trajectories to diverge into substantially different reasoning prefixes. In this context, RL algorithms such as GRPO prove limited: an outcome reward is too sparse to be attributed to specific actions like intermediate steps, and comparisons across sampled traces are non-trivial because they are heterogeneous. To mitigate both the computational cost of repeated sampling and the difficulty of credit assignment, we study single-rollout proximal policy optimization (SR-PPO) featuring token-level credit assignment in RL for language models. Instead of estimating advantages by normalizing episodic returns within the candidate group, we train a calibrated token-level credit critic using Monte Carlo outcomes from one rollout per prompt. Specifically, we use the critic to predict the Pass@k success probability at the prompt prefix, which is derived from a Pass@1 attempt. This choice yields a more selective learning signal than Pass@1: it discounts easily solved prefixes while prioritizing hard ones whose success probability remains marginal. We show that as $k$ increases, Pass@k converges to a reachability indicator, reflecting whether a prefix can lead to at least one successful continuation. In an explicit state graph, the limit ($k \rightarrow \infty$) can be computed in $O(|V|+|E|)$ time, offering a promising surrogate for direct credit assignment without the need to sample contrastive traces. As an initial validation, SR-PPO exhibits stable learning dynamics, along with consistent gains in Pass@128 success rates on mathematical reasoning benchmarks such as HMMT26 and AIME24.

cs.LG↗
arXiv2026

Quantum codes and optimal pure quantum $(r,\delta)$-LRCs via the MP construction

In this paper, we employ MP codes whose defining matrices are $\tau$-optimal defining ($\tau$-OD) matrices to construct new quantum codes and quantum $(r,\delta)$-LRCs. Specifically, we report the following results: We establish a unified $\tau$-monomial decomposition theorem for invertible self-adjoint matrices over finite fields of arbitrary characteristic, which generalizes the result in "Quantum codes using the $\tau$-OD MP construction" where the characteristic was required to be odd. Based on this theorem, we prove the existence of $\tau$-OD matrices over $\mathbb{F}_{q^2}$ for any characteristic and demonstrate that there exist several new infinite families of $\tau$-OD matrices over $\mathbb{F}_{q^2}$ of characteristic $2$. As an application of MP codes involving $\tau$-OD matrices, we construct several infinite families of quantum codes with flexible parameters. Within this framework, we present $222$ record-breaking quantum codes that surpass the best-known records maintained in Grassl's database. We propose two effective schemes for constructing optimal pure quantum $(r,\delta)$-LRCs via MP codes. Accordingly, we construct four new infinite families of optimal pure quantum $(r,\delta)$-LRCs with flexible parameters. Notably, we report an interesting phenomenon by exhibiting $30$ optimal pure quantum $(r,\delta)$-LRCs derived from our framework; that is, there exist quantum codes that are not only optimal pure quantum $(r,\delta)$-LRCs but also, according to Grassl's database, best-known, optimal, or record-breaking quantum codes. To the best of our knowledge, the new discovery that quantum codes are simultaneously optimal pure quantum $(r,\delta)$-LRCs and record-breaking quantum codes has not been previously reported in the literature.

quant-ph↗
arXiv2026

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

cs.AI↗
arXiv2026

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess models in offline settings. In contrast, the performance of a streaming VLM depends on additional metrics beyond pure video understanding, including proactiveness, which reflects the timeliness of the model's responses, and consistency, which captures the robustness of its responses over time. To address this limitation, we propose VSAS-Bench, a new framework and benchmark for Visual Streaming Assistants. In contrast to prior benchmarks that primarily employ single-turn question answering on video inputs, VSAS-Bench features temporally dense annotations with over 18,000 annotations across diverse input domains and task types. We introduce standardized synchronous and asynchronous evaluation protocols, along with metrics that isolate and measure distinct capabilities of streaming VLMs. Using this framework, we conduct large-scale evaluations of recent video and streaming VLMs, analyzing the accuracy-latency trade-off under key design factors such as memory buffer length, memory access policy, and input resolution, yielding several practical insights. Finally, we show empirically that conventional VLMs can be adapted to streaming settings without additional training, and demonstrate that these adapted models outperform recent streaming VLMs. For example, Qwen3-VL-4B surpasses Dispider, the best streaming VLM on our benchmark, by 3% under the asynchronous protocol. The benchmark and code will be available at https://github.com/apple/ml-vsas-bench.

cs.CV↗
arXiv2026

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action heads incur high latency and compute, making real-time control expensive on commodity hardware. We present A1, a fully open-source and transparent VLA framework designed for low-cost, high-throughput inference without sacrificing manipulation success; Our approach leverages pretrained VLMs that provide implicit affordance priors for action generation. We release the full training stack (training code, data/data-processing pipeline, intermediate checkpoints, and evaluation scripts) to enable end-to-end reproducibility. Beyond optimizing the VLM alone, A1 targets the full inference pipeline by introducing a budget-aware adaptive inference scheme that jointly accelerates the backbone and the action head. Specifically, we monitor action consistency across intermediate VLM layers to trigger early termination, and propose Inter-Layer Truncated Flow Matching that warm-starts denoising across layers, enabling accurate actions with substantially fewer effective denoising iterations. Across simulation benchmarks (LIBERO, VLABench) and real robots (Franka, AgiBot), A1 achieves state-of-the-art success rates while significantly reducing inference cost (e.g., up to 72% lower per-episode latency for flow-matching inference and up to 76.6% backbone computation reduction with minor performance degradation). On RoboChallenge, A1 achieves an average success rate of 29.00%, outperforming baselines including pi0(28.33%), X-VLA (21.33%), and RDT-1B (15.00%).

cs.RO↗
arXiv2026

Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors

Achieving fine-grained and structurally sound controllability is a cornerstone of advanced visual generation. Existing part-based frameworks treat user-provided parts as an unordered set and therefore ignore their intrinsic spatial and semantic relationships, which often results in compositions that lack structural integrity. To bridge this gap, we propose Graph-PiT, a framework that explicitly models the structural dependencies of visual components using a graph prior. Specifically, we represent visual parts as nodes and their spatial-semantic relationships as edges. At the heart of our method is a Hierarchical Graph Neural Network (HGNN) module that performs bidirectional message passing between coarse-grained part-level super-nodes and fine-grained IP+ token sub-nodes, refining part embeddings before they enter the generative pipeline. We also introduce a graph Laplacian smoothness loss and an edge-reconstruction loss so that adjacent parts acquire compatible, relation-aware embeddings. Quantitative experiments on controlled synthetic domains (character, product, indoor layout, and jigsaw), together with qualitative transfer to real web images, show that Graph-PiT improves structural coherence over vanilla PiT while remaining compatible with the original IP-Prior pipeline. Ablation experiments confirm that explicit relational reasoning is crucial for enforcing user-specified adjacency constraints. Our approach not only enhances the plausibility of generated concepts but also offers a scalable and interpretable mechanism for complex, multi-part image synthesis. The code is available at https://github.com/wolf-bailang/Graph-PiT.

cs.CV↗
arXiv2026

ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation

Vision-Language-Action (VLA) models and world-action models have emerged as central paradigms for general-purpose robotic intelligence, yet their empirical progress remains constrained by the absence of evaluation protocols that are both physically realistic and diagnostically controlled. Simulator-centric benchmarks provide scale and reproducibility, but cannot fully capture the reality gap induced by perception noise, contact dynamics, latency, calibration error, and hardware constraints. Conversely, real-robot evaluations are often fragmented across platforms, scenes, objects, and scoring rules, making fair comparison and failure attribution difficult. We introduce ManipArena, a standardized real-robot evaluation framework for studying manipulation generalization under matched physical conditions. ManipArena comprises 20 tasks, 10,812 expert trajectories, 13.5M frames, and approximately 188 robot hours across tabletop and mobile manipulation. The framework combines schema-defined task variation, stratified in-domain, visualshift, and semantic-OOD trials, subtask-level partial-credit scoring, three-level language annotations, low-level motor signals, and paired real-to-sim environments reconstructed from physical scenes. Using ManipArena, we evaluate seven tabletop configurations spanning VLA and world-action-model policies. The results show that real-robot conclusions depend not only on architecture, but also on model provenance, fine-tuning regime, data sampling, and annotation granularity. ManipArena thus provides a reproducible and interpretable foundation for diagnosing capability boundaries and failure modes in embodied generalization.

cs.RO↗
arXiv2026

Incentivizing Temporal-Awareness in Egocentric Video Understanding Models

Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training objectives that fail to explicitly reward temporal reasoning and instead rely on frame-level spatial shortcuts. To address this limitation, we propose Temporal Global Policy Optimization (TGPO), a reinforcement learning with verifiable rewards (RLVR) algorithm designed to incentivize temporal awareness in MLLMs. TGPO contrasts model outputs generated from temporally ordered versus shuffled video frames to derive calibrated, globally normalized reward signals that explicitly favor temporally coherent reasoning. Integrated with GRPO and GSPO, TGPO supports cold-start RL training and effectively suppresses spatial shortcut behaviors learned by existing MLLMs. Experiments across five egocentric video benchmarks demonstrate that TGPO consistently improves temporal grounding and causal coherence, outperforming prior RL-based video reasoning approaches. Our results suggest that TGPO offers a simple and scalable pathway toward temporally robust MLLMs for egocentric video understanding.

cs.CV↗
arXiv2026

Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism

Current label-free RLVR approaches for large language models (LLMs), such as TTRL and Self-reward, have demonstrated effectiveness in improving the performance of LLMs on complex reasoning tasks. However, these methods rely heavily on accurate pseudo-label estimation and converge on spurious yet popular answers, thereby trapping in a dominant mode and limiting further improvements. Building on this, we propose Dual Consensus Reinforcement Learning (DCRL), a novel self-supervised training method which is capable of generating more reliable learning signals through a two-stage consensus mechanism. The model initially acts as an anchor, producing dominant responses; then it serves as an explorer, generating diverse auxiliary signals via a temporary unlearning process. The final training target is derived from the harmonic mean of these two signal sets. Notably, the process operates entirely without external models or supervision. Across eight benchmarks and diverse domains, DCRL consistently improves Pass@1 over majority vote while yielding more stable training dynamics. These results demonstrate that DCRL establishes a scalable path toward stronger reasoning without labels.

cs.LG↗
arXiv2026

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning \& Action-planning), a benchmark that uniquely unifies time-evolving personal context with an interactive toolbox and complex user intents. Our event-driven pipeline generates 2,413 scenarios across four protagonists, grounded in longitudinal life events and annotated by referential, functional, and informational complexity. Evaluation of state-of-the-art models (e.g., Claude-4.5-Opus, DeepSeek-V3.2) reveals significant performance degradation under high-complexity conditions, with argument generation emerging as the primary bottleneck. These findings expose critical limitations in current agents' ability to ground reasoning within messy personal context and orchestrate reliable multi-step plans. We release ASTRA-bench with a full execution environment and evaluation scripts to provide a diagnostic testbed for developing truly context-aware AI assistants.

cs.AI↗
arXiv2026

Multi-Agent Teams Hold Experts Back

Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully designed in advance and must instead emerge through interaction. However, most prior work enforces coordination through fixed roles, workflows, or aggregation rules, leaving open the question of how well self-organizing teams perform when coordination is unconstrained. Drawing on organizational psychology, we study whether self-organizing LLM teams achieve strong synergy, where team performance matches or exceeds the best individual member. Across human-inspired and frontier ML benchmarks, we find that -- unlike human teams -- LLM teams consistently fail to match their expert agent's performance, even when explicitly told who the expert is, incurring performance losses of up to 41.1% on ML benchmarks. Decomposing this failure, we show that expert leveraging, rather than identification, is the primary bottleneck. Conversational analysis reveals a tendency toward integrative compromise -- averaging expert and non-expert views rather than appropriately weighting expertise -- which increases with team size and correlates negatively with performance. Interestingly, this consensus-seeking behavior improves robustness to adversarial agents, suggesting a trade-off between alignment and effective expertise utilization. Our findings reveal a significant gap in the ability of self-organizing multi-agent teams to harness the collective expertise of their members.

cs.MA↗
arXiv2026

Negatives-Dominant Contrastive Learning for Generalization in Imbalanced Domains

Imbalanced Domain Generalization (IDG) focuses on mitigating both domain and label shifts, both of which fundamentally shape the model's decision boundaries, particularly under heterogeneous long-tailed distributions across domains. Despite its practical significance, it remains underexplored, primarily due to the technical complexity of handling their entanglement and the paucity of theoretical foundations. In this paper, we begin by theoretically establishing the generalization bound for IDG, highlighting the role of posterior discrepancy and decision margin. This bound motivates us to focus on directly steering decision boundaries, marking a clear departure from existing methods. Subsequently, we technically propose a novel Negative-Dominant Contrastive Learning (NDCL) for IDG to enhance discriminability while enforce posterior consistency across domains. Specifically, inter-class decision-boundary separation is enhanced by placing greater emphasis on negatives as the primary signal in our contrastive learning, naturally amplifying gradient signals for minority classes to avoid the decision boundary being biased toward majority classes. Meanwhile, intra-class compactness is encouraged through a re-weighted cross-entropy strategy, and posterior consistency across domains is enforced through a prediction-central alignment strategy. Finally, rigorous yet challenging experiments on benchmarks validate the effectiveness of our NDCL. The code is available at https://github.com/Alrash/NDCL.

cs.LG↗
arXiv2026

DynaWeb: Model-Based Reinforcement Learning of Web Agents

The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by the challenges of interacting with the live internet, which is inefficient, costly, and fraught with risks. Model-based reinforcement learning (MBRL) offers a promising solution by learning a world model of the environment to enable simulated interaction. This paper introduces DynaWeb, a novel MBRL framework that trains web agents through interacting with a web world model trained to predict naturalistic web page representations given agent actions. This model serves as a synthetic web environment where an agent policy can dream by generating vast quantities of rollout action trajectories for efficient online reinforcement learning. Beyond free policy rollouts, DynaWeb incorporates real expert trajectories from training data, which are randomly interleaved with on-policy rollouts during training to improve stability and sample efficiency. Experiments conducted on the challenging WebArena and WebVoyager benchmarks demonstrate that DynaWeb consistently and significantly improves the performance of state-of-the-art open-source web agent models. Our findings establish the viability of training web agents through imagination, offering a scalable and efficient way to scale up online agentic RL.

cs.CL↗
arXiv2026

Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos

Understanding the physical world, including object dynamics, material properties, and causal interactions, remains a core challenge in artificial intelligence. Although recent multi-modal large language models (MLLMs) have demonstrated impressive general reasoning capabilities, they still fall short of achieving human-level understanding of physical principles. Existing datasets for physical reasoning either rely on real-world videos, which incur high annotation costs, or on synthetic simulations, which suffer from limited realism and diversity. In this paper, we propose a novel paradigm that leverages glitches in gameplay videos, referring to visual anomalies that violate predefined physical laws, as a rich and scalable supervision source for physical world understanding. We introduce PhysGame, an meta information guided instruction-tuning dataset containing 140,057 glitch-centric question-answer pairs across five physical domains and sixteen fine-grained categories. To ensure data accuracy, we design a prompting strategy that utilizes gameplay metadata such as titles and descriptions to guide high-quality QA generation. Complementing PhysGame, we construct GameBench, an expert-annotated benchmark with 880 glitch-identified gameplay videos designed to evaluate physical reasoning capabilities. Extensive experiments show that PhysGame significantly enhances both Game2Real transferability, improving the real world physical reasoning performance of Qwen2.5VL by 2.5% on PhysBench, and Game2General transferability, yielding a 1.9% gain on the MVBench benchmark. Moreover, PhysGame-tuned models achieve a 3.7% absolute improvement on GameBench, demonstrating enhanced robustness in detecting physical implausibilities. These results indicate that learning from gameplay anomalies offers a scalable and effective pathway toward advancing physical world understanding in multimodal intelligence.

cs.CV↗