arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 199 records · Page 11Linked to original sources

arXiv2026

Universal Concept Disruption for SAM3 Image Segmentation

SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding model decides whether a concept is present and segments all matching instances. While this presence-gated design improves concept-level prediction, its adversarial robustness remains unexplored. In this paper, we introduce Universal Concept Disruption (UCD), the first universal cross-concept adversarial attack tailored to SAM3 image segmentation. UCD learns a single bounded image perturbation from (image, noun-phrase) pairs and attacks SAM3 as an integrated concept-grounding system. It jointly disrupts the text-conditioned input path, maximizes divergence in prompt-shared visual features, suppresses the final presence-gated concept scores, and corrupts the spatial validity of retained masks through area collapse and clean-mask Dice disruption. Across SACo-Gold, LVIS, RefCOCO, PhraseCut, and OpenImages datasets, UCD consistently outperforms all baselines under a matched evaluation protocol, reducing average mask AP from 59.43 to 18.73 and average cgF1 from 50.32 to 20.49. The learned perturbation also transfers to SAM3.1 and to SAM3 video inference without re-optimization, while prompt ensembling, lightweight head fine-tuning, and temporal filtering provide limited recovery.

cs.CV↗

arXiv2026

Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces

Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time. We observe that, even after DR Agentic Reinforcement Learning (DR-RL), 61.6% of the model's remaining prediction errors can still be attributed to insufficient long-context understanding, including longcontext hallucination and failures in cross-document evidence integration. It motivates us to further break the bottleneck of DR-RL by strengthening the model's long-context ability. However, effective LongContext training requires more than simply increasing context length. To bridge the data gap, we propose `DR Rollouts to LongContext-QA (DR-to-Long)'. The method repurposes DR-RL trajectories, which naturally contain search histories, visited webpages, evidence snippets, and final-answer supervision. It then replaces the compact snippets and webpage summaries in each trajectory with the full contents of their corresponding URLs, producing substantially longer multi-document contexts while preserving the original evidence relationships. Building on DR-to-Long, we introduce DLD (DR -> LongQA -> DR)-RL. DLD-RL first performs a short DR-RL stage to collect rollout trajectories, which are then converted into LongQA instances at zero annotation cost. The model is subsequently optimized with LongQA-RL to strengthen LongContext ability, followed by full DR-RL to continue improving its DR capability. Experiments show that DLD-RL outperforms standard DR-RL by 7.3% on three Deepresearch benchmarks and improves performance by 13.5% on three long-context benchmarks.

cs.CL↗

arXiv2026

Training Documents Reranker with Search Rubrics for Deep Research Agent

Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$ documents may not form a \textit{set} that satisfies the complex information needs of an agent query (\eg, diverse, concise and authoritative documents). In this paper, we propose search-oriented rubrics that \textit{explicitly} define the requirements that high-quality document sets should satisfy for each agent query. Our search rubrics are organized into a hierarchical structure and synthesized using a powerful LLM. Based on these search rubrics, we further train a document reranker \textbf{RubricRanker} to select a high-quality subset from retrieved documents. We design a two-stage training framework that consists of rubrics-guided supervised fine-tuning and rubric-based reinforcement learning. Extensive experiments demonstrate that RubricRanker outperforms the strongest baseline by 2.6 points on four deep research benchmarks and generalizes well to five RAG benchmarks.

cs.IR↗

arXiv2026

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing methods have evolved along two directions. One line dynamically retrieves target-relevant behaviors from long histories, enabling target-aware modeling but requiring target-dependent computation during inference. The other line compresses entire behavior sequences into compact user representations, achieving high efficiency and scalability but sacrificing target-specific adaptation due to target-independent encoding. The key challenge is therefore to enable target-aware modeling while preserving the efficiency and scalability of compressed user representations. To address this challenge, we propose \textbf{SITA}, a target-aware compression framework for long-sequence recommendation. SITA enables target-aware compression by organizing compressed interests into semantic structures through semantic identifiers learned via parallel semantic quantization. Conditioned on the semantic identifier of the target item, SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation. Extensive experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines while maintaining strong scalability, highlighting its strong potential for real-world recommender systems.

cs.IR↗

arXiv2026

Out-Of-The-Loop Multi-Fidelity Bayesian Optimization

Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expensive objective functions with cheaper lower-fidelity proxies available. Multi-fidelity Bayesian optimization (MF-BO) is a principled approach to this problem, leveraging correlations across different fidelities when querying the objective. However, for many important MF-BO tasks, the true highest-fidelity function is prohibitively expensive to be part of the optimization loop. Nevertheless, practitioners often have gold standard data (observations of the highest-fidelity function) obtained from previous experiments that might provide information for the current task. For instance, in molecular optimization, chemists often pick the top-$k$ candidate molecules using various computer simulations, and later reveal their true objective function values. In this work, we demonstrate the suboptimality of standard MF-BO algorithms in the real-world scenarios above, even under ideal assumptions. Next, we mitigate this problem by incorporating historical high-fidelity data accompanied by task descriptors---which can be explicitly given or extracted from unstructured metadata. We demonstrate the effectiveness of our methods on synthetic functions, as well as real-world problems in chemistry and hyperparameter optimization.

cs.LG↗

arXiv2026

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

Agents built around large language models continually accumulate interaction trajectories during deployment, yet their behavior typically remains fixed. Beyond updating model weights, these trajectories can improve the agent harness that constructs context, mediates tools, validates actions, and recovers execution. We introduce Harness-R1, the first method, to our knowledge, that makes failure-conditioned, lifecycle-wide editing of an existing executable runtime a learned capability. It post-trains a dedicated harness engineer with online reinforcement learning so that its edits are optimized for the realized task success they produce, rather than proposed by a fixed editor. A separate 9B engineer converts batches of target-agent failures into validated executable patches; fresh same-batch reruns of the frozen target provide outcome rewards, so training updates only the engineer. Cold-start supervised fine-tuning initializes this editing policy, which is then trained online with group-relative policy optimization. Across WebShop, ALFWorld, and DBBench, Harness-R1 raises vanilla Qwen3.5-9B success from 44.3% to 53.6% (+9.3 percentage points). After direct target-agent fine-tuning, a target-specific engineer raises the average further from 59.2% to 64.2% (+5.0 points); because these gains hold both before and after fine-tuning the target, Harness-R1 points toward co-evolving the harness engineer and the target agent.

cs.AI↗

arXiv2026

EnvShip: A Unified Framework for Context-Aware and Cross-Region Vessel Trajectory Forecasting

Accurate vessel trajectory forecasting is essential for maritime situational awareness, navigation safety, traffic management, and autonomous navigation. Public Automatic Identification System (AIS) archives have enabled extensive research in this area, yet results remain difficult to compare because existing studies use incompatible preprocessing pipelines, forecasting horizons, data splits, coordinate systems, contextual inputs, and evaluation settings. We present EnvShip, a unified multi-region framework for context-aware and cross-region vessel trajectory forecasting. EnvShip applies a fixed and reproducible pipeline to public AIS data from Denmark, the United States, Greece, and Norway, and defines two standardized forecasting tracks spanning short- and long-horizon settings. From large-scale processed data, we curate 330{,}000 short-term and 106{,}857 long-horizon samples through strict motion screening, vessel-category and difficulty stratification, redundancy control, and vessel-disjoint splits. Each sample is aligned with environmental and neighboring-vessel context, together with weather and sea-state variables where available. We evaluate representative methods under in-domain and cross-region protocols, with analyses across prediction difficulty, scene type, and random seeds. Results show that environmental context provides the largest gains in coastline-constrained scenes, whereas neighboring-vessel context primarily benefits interaction-rich cases. Multi-region training improves generalization in most settings but introduces negative transfer for some source combinations. EnvShip provides a common and reproducible testbed for vessel trajectory forecasting. Code and data are publicly available at https://huggingface.co/datasets/mark000071/envship_v2_datasets.

cs.LG↗

arXiv2026

LLM-Assisted Coalition Formation for Cooperative Perception in Autonomous Driving

Cooperative perception (CP) enables connected autonomous vehicles (CAVs) to share complementary observations for safer navigation, but practical deployment is limited by bandwidth constraints, unreliable links, and redundant information exchange. Existing CP methods often assume predefined participants and merely focus on collective perception. Likewise, recent LLM-based cooperative driving frameworks facilitate multi-vehicle reasoning but do not regulate participation criteria to select more beneficial vehicles. To bridge this gap, we propose an LLM-assisted coalition formation framework that selects the most informative helper vehicles before LLM reasoning. The approach jointly optimizes perceptual diversity using a determinantal point process (DPP) over multimodal vehicle embeddings and communication-aware reliability. This leads to a joint coalition selection and power allocation problem, which we solve efficiently via a relaxed convex reformulation and an ADMM-based optimization strategy that decouples diversity-aware selection from network-aware resource allocation. The selected coalition is then summarized and provided with an LLM reasoning module for efficient and less redundant multi-vehicle decision support. Experimental results show that our approach outperforms other baselines in overall coalition value, while maintaining high diversity and improved networking efficiency. The framework achieves a better balance between task performance and safety across OPV2V and V2V4Real datasets, demonstrating its effectiveness for cooperative autonomous driving with communication constraints.

cs.NI↗

arXiv2026

Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents

As LLM-based conversational agents advance toward increasingly open-ended and interaction-intensive scenarios, task completion alone provides an incomplete assessment of their effectiveness. The evolution of users' internal states, including beliefs, desires, intentions, and emotions (BDI/E), serves as an intermediate signal connecting agent behaviors with interaction outcomes and reflects how conversational strategies shape users during multi-turn interactions. However, existing evaluation paradigms primarily focus on surface-level responses or final outcomes, providing limited insight into the underlying cognitive processes. This limitation makes it difficult to diagnose why agents succeed or fail and to optimize their interaction strategies. To address this challenge, we propose Cognitive World Model (CogWM), an LLM-based cognitive user model that jointly models users' BDI/E states and corresponding responses, enabling explicit cognitive trajectory tracking. Trained on 150K user-turn samples with Qwen3-14B, CogWM achieves superior performance over existing user simulation baselines in both response fidelity and cognitive state understanding. Interactions with six state-of-the-art LLMs demonstrate that CogWM enables progressive comparison of agents through cognitive trajectories, revealing distinct agent patterns and complementary relationships between cognitive evolution and behavioral outcomes.

cs.AI↗

arXiv2026

Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework

The effectiveness of modern visual representation learning and autoregressive models critically depends on vector quantization (VQ), which discretizes continuous feature representations using a learnable codebook. Despite its widespread use, existing VQ methods often suffer from training instability and codebook collapse, arising from gradient mismatch induced by the straight-through estimator and the under-utilization of code vectors. In this work, we show that both issues can be traced to a fundamental mismatch between the distributions of feature vectors and code vectors, leading to inefficient representation and information loss. Building on this observation, we propose a distributional matching framework for vector quantization. We introduce principled criteria for desirable VQ behavior and demonstrate through theoretical analysis and empirical evaluation that aligning feature and code vector distributions provides a unifying mechanism for mitigating training instability and codebook collapse. We instantiate this framework using a Wasserstein-based objective with an efficient closed-form under a mild Gaussian approximation, and further show that a nonparametric alternative based on maximum mean discrepancy yields comparable performance. Extensive experiments on visual tokenization benchmarks support the effectiveness and robustness of the proposed approach.

cs.CV↗

arXiv2026

WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval

Text-Motion Retrieval (TMR) aims to retrieve 3D motion sequences semantically relevant to text descriptions. However, matching 3D motions with text remains highly challenging, primarily due to the intricate structure of the human body and its spatiotemporal dynamics. Existing approaches often overlook these complexities, relying on general encoding methods that fail to distinguish different body parts and their dynamics, limiting precise semantic alignment. To address this, we propose WaMo, a novel wavelet-based multi-frequency feature extraction framework. It fully captures joint-specific and time-varying motion details at multiple resolutions for individual joint trajectories, extracting discriminative motion features to achieve fine-grained alignment with texts. WaMo has three key components: (1) Trajectory Wavelet Decomposition decomposes motion signals into frequency components that preserve both local kinematic details and global motion semantics. (2) Trajectory Wavelet Reconstruction uses learnable inverse wavelet transforms to reconstruct original joint trajectories from extracted features, ensuring the preservation of essential spatiotemporal information. (3) Disordered Motion Sequence Prediction reorders shuffled motion sequences to improve learning of inherent temporal coherence, enhancing motion-text alignment. Extensive experiments demonstrate WaMo's superiority, achieving 17.0\% and 18.2\% relative improvements in $Rsum$ on HumanML3D and KIT-ML datasets, respectively, outperforming existing state-of-the-art (SOTA) methods. Code is available at https://github.com/3DAgentWorld/WaMo/.

cs.CV↗

arXiv2026

Heterogeneous Element-Aware Cross-Version Differencing of Scientific Documents via Layout-Aware Alignment and Structure-Aware Reasoning

Cross-version differencing of scientific documents is essential in scholarly publishing and technical documentation, but remains challenging because scientific documents are page-structured artifacts containing heterogeneous elements such as text, tables, formulas, figures, and layout cues. Existing text-sequence-based methods often lose layout and structural information, while image-based methods lack semantic interpretability and are sensitive to rendering variation. To address these limitations, this paper proposes a layout-aware heterogeneous element-aware framework for scientific document differencing. The framework decomposes document versions into semantically typed elements, establishes cross-version correspondence through an alignment-first mechanism that jointly models spatial, content, and structural compatibility, and performs type-aware difference reasoning over aligned element pairs. It supports unified change detection, localization, structure-awareness analysis, and alignment/matching evaluation across text, tables, formulas, and figures. Experiments on real-world scientific PDF data from journal production proofreading workflows show that the proposed framework consistently outperforms element-specific baselines. It achieves detection F1 scores of 0.903, 0.855, 0.862, and 0.845 for text, tables, formulas, and figures, respectively, with further improvements in localization, structure awareness, and matching quality. Ablation and sensitivity analyses confirm the effectiveness of cross-version alignment, type-specific representations, structure-aware reasoning, and compatibility-weight design. These results demonstrate that heterogeneous element-aware differencing provides a robust and interpretable solution for scientific document comparison in realistic editorial production scenarios.

cs.CL↗

arXiv2026

Interpretable GOHR Agents via Sparse Autoencoders

A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We report interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR). We focus on a compact two-rule task in which both hidden rules map object shapes to target buckets, but with different permutations. The policy is trained on episodes sampled from these two hidden rules and then evaluated with fixed weights. It is never given a rule label and does not use an explicit rule classifier; any rule information must be inferred implicitly from interaction history. In this setting, the correct rule is not identifiable before the agent tries an informative move and observes accept/reject feedback. Sparse autoencoders (SAEs) trained on the agent's decision-token embeddings recover this structure. When held-out decisions are labeled by simple concepts such as the chosen shape or bucket, SAE dimensions that are highly selective for a concept cover most decisions where that concept is present. Individual SAE dimensions also correspond to interpretable strategies such as probing one rule hypothesis and switching after negative feedback.

cs.LG↗

arXiv2026

CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games

Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collaboration. While recent advances in large language models (LLMs) have driven significant progress in SDG agents, current approaches are predominantly text-based, overlooking the multimodal nature that is fundamental to human social interaction. To bridge this gap, we introduce CaM-Wolf, the first SDG agent that integrates multimodal perception and generation. CaM-Wolf processes video inputs from other players, employs a causal-aware Reasoner trained via reinforcement learning to establish logical chains between observable behaviors and hidden roles, and presents itself through an animated avatar. Our experiments and user study show that CaM-Wolf achieves superior agent gameplay performance and enhances the quality of human-AI interaction. This work represents a significant advancement towards creating more human-like AI agents capable of participating in nuanced social dynamics. Our code is available at https://3dagentworld.github.io/avatar_wolf.

cs.AI↗

arXiv2026

$M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation

Aligning Large Language Models (LLMs) with human preferences is pivotal for Machine Translation (MT), yet current approaches are often hindered by misleading reward signals. Our analysis reveals that prevailing Quality Estimation (QE) models exhibit a systematic blind spot toward partial errors, specifically partial hallucinations and omissions, often favoring superficially fluent but unfaithful translations. To address this issue, we propose $M^2PO$ (Multi-Perspective Multi-Pair Preference Optimization), a data-centric framework for preference optimization in machine translation. First, to correct the bias toward fluency, $M^2PO$ uses a dual-perspective mechanism that decouples semantic fidelity from fluency and prioritizes faithfulness through a curriculum strategy. Second, after correcting this bias, partial errors fall between perfect and severely incorrect translations, making them difficult to learn through standard best-versus-worst comparisons. We therefore introduce a multi-pair objective that leverages the full candidate list to capture these fine-grained error signals. Experiments on WMT23, WMT24, and FLORES-200 show that $M^2PO$ enables a 9B model to outperform leading open-source baselines and achieve parity with proprietary models such as GPT-4o and Gemini-2.0-Flash, demonstrating strong potential for efficient and high-fidelity LLM-based translation. Our code and dataset will be released.

cs.CL↗

arXiv2026

VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation

Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization. However, these artificial codes may overcompress item semantics, remain misaligned with pretrained LLM vocabularies, and require costly autoregressive decoding. In light of this, we propose VaLiDRec, a generative recommendation framework based on variable-length, LLM-aligned semantic identifiers. VaLiDRec constructs SIDs directly from informative native LLM vocabulary tokens via token importance estimation, semantic-quality-aware pruning, and collision-aware refinement, allowing identifier lengths to adapt to item semantic complexity. To model user preferences, VaLiDRec incorporates graph-aware soft prompts and reformulates recommendation as token-set prediction with token-level item scoring, eliminating autoregressive SID generation and beam search. Experiments on four real-world datasets show that VaLiDRec consistently outperforms strong sequential and generative recommendation baselines across all evaluation metrics. It further achieves superior zero-shot item cold-start performance and 87.49$\times$ faster inference than LC-Rec. These results demonstrate that LLM-native variable-length semantic identifiers provide a more expressive and efficient paradigm for generative recommendation.

cs.IR↗

arXiv2026

Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while supporting 16 languages, 20 Chinese dialect regions, one-pass long-form synthesis up to 3 minutes, and robust generation from noisy, reverberant, or unclear reference speech. Across SEED-TTS-Eval, CV3-Eval, instruction-following, long-form, and acoustic-robustness evaluations, Qwen-Audio-3.0-TTS achieves state-of-the-art performance on many reported dimensions or the strongest aggregate results. It also ranks first on the independent Artificial Analysis Text-to-Speech Leaderboard. These results establish Qwen-Audio-3.0-TTS as a strong foundation for production-level speech synthesis.

eess.AS↗

arXiv2026

PRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image Generation

Text-to-image generation models can synthesize high-quality images from natural language descriptions, but their performance remains highly sensitive to prompt formulation. Existing prompt optimization methods mainly rely on text-side rewriting, prompt expansion, or external reward signals, offering limited image-grounded diagnosis and weak support for learning reusable optimisation policies. In this paper, we propose PRISM, a Prompt Refinement framework via Image-grounded Self-rewarding Mechanism. PRISM closes the prompt-image-feedback loop by interpreting generated images with structured visual diagnosis and scoring them along semantic consistency, aesthetic quality, and human preference alignment. It first initializes a unified VLM through multi-task supervised fine-tuning, and then improves the prompt policy via self-rewarding optimization with a hybrid ideal-point and Chebyshev reward. Extensive experiments show that PRISM improves holistic image quality and fine-grained semantic alignment, while providing interpretable feedback for targeted prompt refinement. The code is available at https://anonymous.4open.science/r/PRISM-FF81.

cs.CV↗