Searcharxiv⌕ Search

arXiv subjects

Guanjie Cheng

Publications and source records attributed to Guanjie Cheng.

At least 19 recordsLinked to original sources
arXiv2026

DuSE-Bench: Benchmarking Joint Reasoning over Evolving Dialogue and Documents

Persistent Web information assistants must combine evolving document facts with user requirements established and revised across sessions. Yet systematic evaluation of how changes in both sources affect response requirements and evidence attribution remains limited. To address this gap, we introduce Dual-Source Evolution Benchmark (DuSE-Bench), a benchmark comprising 1,000 tasks across five scenarios, including 700 whose required premises originate in both dialogue and documents. An evolving Support Graph guides task construction and preserves links from updated facts and reused conclusions to original turns and passages. Task annotations distinguish grounding source from state dependence and enable separate evaluation of response content, response type, and source attribution. Experiments across 11 baseline configurations reveal persistent challenges in joint reasoning over evolving dialogue and documents, with content accuracy on jointly grounded tasks reaching at most 56.7%. Moreover, improvements in content accuracy can coincide with poorer response choice, while content-correct responses frequently lack complete attribution to original evidence. Matched evidence substitutions further show that the effect of replacing one source's evidence depends on support from the other. These findings motivate coordinating dialogue memory and document retrieval to apply current user requirements and document facts together while preserving their original support. The data are available at https://github.com/JianfengGao7/DuSE-Bench.

cs.CL↗
arXiv2026

A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions

Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task-centric survey that decomposes long-document visual question answering (VQA) into four components: document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. For each, we develop a fine-grained taxonomy and trace motivations, technical responses, and cross-component connections. We focus on explicit retrieval while covering direct reading. Our temporal analysis traces expanding priorities from multimodal content understanding to sufficient, high-fidelity evidence acquisition and sustained evidence management. We outline future directions in evidence sufficiency, verifiable and correctable understanding, and budget-aware coordination, with an outlook on continual document understanding.

cs.CV↗
arXiv2026

TenonAgent: Virtualizing Execution Residency for Memory-Oversubscribed LLM Agents

LLM agents execute as long-lived, multi-stage workflows with substantial resource-demand variation across phases. Provisioning each agent or sandbox for its lifetime peak leads to low resource utilization, particularly for memory, whereas aggressive oversubscription risks memory contention, out-of-memory failures, and costly workflow retries. This tension limits the concurrency and efficiency of agent serving under constrained host memory. We present TenonAgent, a runtime system that virtualizes sandbox residency by decoupling the logical agent's lifetime from its physical execution environment. To manage memory oversubscription, TenonAgent employs a dual-timescale control plane. At action boundaries, it combines predictive admission control with a fail-closed, restart-safe contract, dynamically materializing or dematerializing sandboxes based on global memory pressure. During active tool execution, a sched_ext-based kernel gate paces sandbox execution permissions to reduce unexpected concurrent memory growth. The gate provides feedback control over future execution opportunities. Evaluations across diverse agentic workloads show that, under the tested workloads and parameter settings, TenonAgent substantially reduces observed OOM failures and achieves a 100% task success rate in bursts reaching an 8.6x memory oversubscription ratio. Overall, it delivers up to a 5.5x speedup over unmanaged execution, outperforms existing agent-level and cgroup-based schedulers by 5x to 37x, and provides consistent benefits across both Docker and Firecracker microVM backends.

cs.OS↗
arXiv2026

Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling

Protein structure modeling rests on a single computational primitive: the interaction between what a residue is (sequence content) and where it sits (three-dimensional geometry). What is the expressive limit of this layer class? We show that the complete bilinear operator over content-geometry outer products--the sufficient statistic of all second-order interactions--is the expressive ceiling, while the additive message passing of mainstream geometric GNNs is provably blind to content-geometry binding. We then introduce Hyper-Fold, a rank-K separable convolutional backbone approaching this ceiling at message-passing cost: each radius neighborhood is organized into a sequence hyperedge and a contact hyperedge, modulated by an edge-conditioned matrix-valued operator factorized into K learned basis operators with geometry-generated coefficients. Across enzyme function prediction, fold classification, and ligand binding site detection, Hyper-Fold and its hierarchical variant Hyper-Fold-Deep achieve the best results among protein-specific structure encoders; Hyper-Fold-Pocket, an anchored set-prediction head, surpasses UniSite-3D on UniSite-DS and two zero-shot benchmarks with no sequence language model features, 68x fewer parameters, and 4.8x lower latency--suggesting that a sufficiently expressive 3D backbone recovers information that fusion architectures previously borrowed from evolution-scale pretraining.

cs.AI↗
arXiv2026

MUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs

On-device multimedia retrieval is vital for smartphones, enabling applications like cross-modal semantic search and multimodal personal AI agents. However, realizing efficient retrieval on mobile SoCs remains a critical systems challenge. Unlike text-based search, multimedia applications depend on high-dimensional cross-modal embeddings (often exceeding 1024 dimensions) and continuously expanding media streams (e.g., video lifelogs and ambient audio). Mobile devices must process these intensive workloads under strict latency, energy, and memory constraints. Existing vector retrieval systems, designed primarily for static server datasets, are poorly suited for the dynamic execution models of mobile SoCs, where interactive queries must coexist with continuous background media ingestion and index maintenance. To address these challenges, we propose MUSE, a MUltimedia Search Engine comprehensively co-designed for mobile SoCs. MUSE tackles these issues through an architecture-index co-design. It introduces a three-stage asynchronous execution pipeline that overlaps DMA transfers, NPU matrix computation, and hardware-vector data adaptation to overcome the memory wall of high-dimensional embeddings. Furthermore, it redesigns the Inverted File Index (IVF) and introduces workload-aware heterogeneous scheduling across the CPU, GPU, and NPU for hybrid interactive-and-ingestion workloads. Evaluated on Snapdragon 8-series SoCs using real-world multimodal datasets, MUSE improves query throughput by up to 1.4x at matched recall, achieves up to 7x faster index construction, and delivers up to 6x higher insertion throughput under concurrent streaming. Crucially, its accelerator-native design ensures strict physical compliance, capping peak device temperatures at 38°C and reducing total energy consumption by up to 4.6x compared to CPU-bound baselines.

cs.DC↗
arXiv2026

FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs

Large language model (LLM) agents autonomously interleave semantic reasoning with complex system operations. In these dynamic environments, static tool-level permissions are fundamentally insufficient; safe authorization is highly context-dependent and heavily reliant on evolving runtime states and data flows. We present FAVA (Formal Authorization for Verified Agents), a permission-carrying authorization framework for agent execution. FAVA utilizes an LLM-guided Permission Intermediate Representation (IR) to translate ambiguous natural-language tasks into structured constraints. A deterministic lowering pass then converts this IR into an evidence-backed permission graph that explicitly tracks data flows, dependencies, and contextual labels. To provide strict security guarantees, a Satisfiability Modulo Theories (SMT) authorizer mathematically verifies the current graph against security policies before any effectful action executes. A runtime gateway then enforces the solver's result, either authorizing the execution or intercepting it with a precise counterexample. We evaluate FAVA across OpenAgentSafety, OctoBench, and ActPlane scenarios. Our evaluation demonstrates that FAVA achieves a 90.5% Decision Compliance Rate (DCR) over the aggregate dataset, successfully intercepting dynamic violating traces in the evaluated trace-conditioned scenarios.

cs.CR↗
arXiv2026

ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding

Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers. We propose ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories. Specifically, ViSAGE anchors entity identity via cross-modal binding over long temporal ranges. It then applies bidirectional memory refinement to propagate delayed identity evidence, retroactively unifying historical records and improving future reasoning. We also introduce multi-agent cross-verification to assess retrieved evidence under an identity-evidence alignment onstraint, enabling abstention instead of unsupported answers when evidence is missing. Extensive results demonstrate that ViSAGE consistently outperforms the strongest baseline, achieving 5.9% higher accuracy.

cs.AI↗
arXiv2026

Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise

Deep multi-view clustering has achieved remarkable progress but remains vulnerable to complex noise in real-world applications. Existing noisy robust methods predominantly rely on a simplified binary assumption, treating data as either perfectly clean or completely corrupted. This overlooks the prevalent existence of heterogeneous observation noise, where contamination intensity varies continuously across data. To bridge this gap, we propose a novel framework termed Quality-Aware Robust Multi-View Clustering (QARMVC). Specifically, QARMVC employs an information bottleneck mechanism to extract intrinsic semantics for view reconstruction. Leveraging the insight that noise disrupts semantic integrity and impedes reconstruction, we utilize the resulting reconstruction discrepancy to precisely quantify fine-grained contamination intensity and derive instance-level quality scores. These scores are integrated into a hierarchical learning strategy: at the feature level, a quality-weighted contrastive objective is designed to adaptively suppress the propagation of noise; at the fusion level, a high-quality global consensus is constructed via quality-weighted aggregation, which is subsequently utilized to align and rectify local views via mutual information maximization. Extensive experiments on five benchmark datasets demonstrate that QARMVC consistently outperforms state-of-the-art baselines, particularly in scenarios with heterogeneous noise intensities.

cs.CV↗
arXiv2026

Agentic Services Computing

Services computing has evolved from Web services and microservices to cloud-native and serverless paradigms. These approaches established mature principles for describing, composing, deploying, operating, and governing reusable software functions. LLM-based agents now introduce a fundamentally different service form. Service value in this paradigm emerges not only from invoking predefined functions but also from delegating goals to autonomous entities. These entities understand context, use tools, collaborate with peers, and act across open environments. This shift raises a core question for services computing. How can goal-driven, stateful, tool-mediated, and accountable autonomous behavior be engineered and managed as a service? Recent studies on LLM agents and multi-agent systems provide important foundations. A clear service-centered research roadmap for this emerging paradigm nevertheless remains absent. This work introduces Agentic Services Computing (ASC) to address this gap. ASC extends services computing from managing reusable functional endpoints to engineering and governing autonomous service entities. It defines agentic services as service-oriented autonomous agents. Related research is organized through a lifecycle view that connects service objects, system structures, enabling infrastructure, evaluation metrics, application evidence, and open challenges. This service-centered perspective establishes a foundation for future service ecosystems. Autonomous agents can thus be systematically described, composed, delivered, monitored, audited, and evolved as first-class services.

cs.SE↗
arXiv2026

Measurement-Driven Diagnosis and Mitigation of Host-CPU Co-location Interference in Single-GPU LLM Serving on a Multi-GPU Server

Host CPUs in GPU servers are often under-used during LLM inference. Co-locating CPU workloads can improve resource use, but it can also seriously hurt serving quality. Existing work mainly improves LLM serving engines or studies CPU-GPU boundary delays. It gives limited guidance on how external CPU workloads affect the serving path and how operators should choose protection policies. This paper studies host-CPU co-location interference in single-GPU LLM serving. We show that the main observed problem is not slower GPU kernels. Instead, CPU workloads amplify long tails in CPU-side serving stages before GPU work is submitted. To capture this effect, we introduce the Core Path Tail Index (CPTI) and Core Tail Suppression (CTS). Based on these metrics, we build CoTail, a measurement-driven diagnostic procedure that screens workload risk, profiles serving-stage tails, selects OS-level protections, and validates decode SLO compliance. In our primary setup, unprotected nginx co-location reduces throughput by 78.8%, increases TTFT by 429.5%, and increases TPOT by 362.4%. CoTail-guided protections improve nginx throughput by up to 4.4x and reduce TPOT by 4.5x. Under a common-baseline deployment SLO, CoTail satisfies all 12 oracle-feasible held-out cases, compared with 10/12 for Always-rt and 11/12 for Macro-only. It also reduces RT usage from 28 to 22 cases and lowers mean co-tenant slowdown from 56.65% to 51.21%.

cs.DC↗
arXiv2026

ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy

Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone (the nucleus) while dynamically activating query-conditioned agents (electrons) during inference. Crucially, a complexity-aware budgeting strategy aligns resource consumption with task demands by estimating query difficulty to strictly regulate electron instantiation. Extensive experiments across six diverse benchmarks demonstrate that \textsc{ATOM} achieves state-of-the-art performance while improving token efficiency by up to $30\%$ compared to strong baselines.

cs.MA↗
arXiv2026

DRAMA: Next-Gen Dynamic Orchestration for Resilient Multi-Agent Ecosystems in Flux

Multi-agent systems (MAS) have demonstrated significant effectiveness in addressing complex problems through coordinated collaboration among heterogeneous agents. However, real-world environments and task specifications are inherently dynamic, characterized by frequent changes, uncertainty, and variability. Despite this, most existing MAS frameworks rely on static architectures with fixed agent capabilities and rigid task allocation strategies, which greatly limits their adaptability to evolving conditions. This inflexibility poses substantial challenges for sustaining robust and efficient multi-agent cooperation in dynamic and unpredictable scenarios. To address these limitations, we propose DRAMA: a Dynamic and Robust Allocation-based Multi-Agent System designed to facilitate resilient collaboration in rapidly changing environments. DRAMA features a modular architecture with a clear separation between the control plane and the worker plane. Both agents and tasks are abstracted as resource objects with well-defined lifecycles, while task allocation is achieved via an affinity-based, loosely coupled mechanism. The control plane enables real-time monitoring and centralized planning, allowing flexible and efficient task reassignment as agents join, depart, or become unavailable, thereby ensuring continuous and robust task execution. The worker plane comprises a cluster of autonomous agents, each with local reasoning, task execution, the ability to collaborate, and the capability to take over unfinished tasks from other agents when needed.

cs.MA↗
arXiv2026

ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing

Mobile edge crowdsensing (MECS) enables large-scale real-time sensing services, but its continuous data collection and transmission pipeline exposes terminal devices to dynamic privacy risks. Existing privacy protection schemes in MECS typically rely on static configurations or coarse-grained adaptation, making them difficult to balance privacy, data utility, and device overhead under changing channel conditions, data sensitivity, and resource availability. To address this problem, we propose ALPINE, a lightweight closed-loop framework for adaptive privacy budget allocation in MECS. ALPINE performs multi-dimensional risk perception on terminal devices by jointly modeling channel, semantic, contextual, and resource risks, and maps the resulting risk state to a privacy budget through an offline-trained TD3 policy. The selected budget is then used to drive local differential privacy perturbation before data transmission, while edge-side privacy-utility evaluation provides feedback for policy switching and periodic refinement. In this way, ALPINE forms a terminal-edge collaborative control loop that enables real-time, risk-adaptive privacy protection with low online overhead. Extensive experiments on multiple real-world datasets show that ALPINE achieves a better privacy-utility trade-off than representative baselines, reduces the effectiveness of membership inference, property inference, and reconstruction attacks, and preserves robust downstream task performance under dynamic risk conditions. Prototype deployment further demonstrates that ALPINE introduces only modest runtime overhead on resource-constrained devices.

cs.LG↗
arXiv2026

SatFusion: A Unified Framework for Enhancing Remote Sensing Images via Multi-Frame and Multi-Source Images Fusion

High-quality remote sensing (RS) image acquisition is fundamentally constrained by physical limitations. While Multi-Frame Super-Resolution (MFSR) and Pansharpening address this by exploiting complementary information, they are typically studied in isolation: MFSR lacks high-resolution (HR) structural priors for fine-grained texture recovery, whereas Pansharpening relies on upsampled low-resolution (LR) inputs and is sensitive to noise and misalignment. In this paper, we propose SatFusion, a novel and unified framework that seamlessly bridges multi-frame and multi-source RS image fusion. SatFusion extracts HR semantic features by aggregating complementary information from multiple LR multispectral frames via a Multi-Frame Image Fusion (MFIF) module, and integrates fine-grained structural details from an HR panchromatic image through a Multi-Source Image Fusion (MSIF) module with implicit pixel-level alignment. To further alleviate the lack of structural priors during multi-frame fusion, we introduce an advanced variant, SatFusion*, which integrates a panchromatic-guided mechanism into the MFIF stage. Through structure-aware feature embedding and transformer-based adaptive aggregation, SatFusion* enables spatially adaptive feature selection, strengthening the coupling between multi-frame and multi-source representations. Extensive experiments on four benchmark datasets validate our core insight: synergistically coupling multi-frame and multi-source priors effectively resolves the fragility of existing paradigms, delivering superior reconstruction fidelity, robustness, and generalizability.

eess.IV↗
arXiv2026

ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics

The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.

cs.AI↗
arXiv2026

TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training

Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to inefficient training and suboptimal generalization. Existing data selection methods are either heuristic-based, suffering from bias and limited diversity, or data-driven but task-agnostic, failing to optimize for multi-task scenarios. To address these gaps, we introduce TADS (Task-Aware Data Selection), a novel framework for multi-task multimodal pre-training that integrates Intrinsic Quality, Task Relevance, and Distributional Diversity into a learnable value function. TADS employs a comprehensive quality assessment system with unimodal and cross-modal operators, quantifies task relevance via interpretable similarity vectors, and optimizes diversity through cluster-based weighting. A feedback-driven meta-learning mechanism adaptively refines the selection strategy based on proxy model performance across multiple downstream tasks. Experiments on CC12M demonstrate that TADS achieves superior zero-shot performance on benchmarks like ImageNet, CIFAR-100, MS-COCO, and Flickr30K, using only 36% of the data while outperforming baselines by an average of 1.0%. This highlights that TADS significantly enhances data efficiency by curating a high-utility subset that yields a much higher performance ceiling within the same computational constraints.

cs.LG↗
arXiv2026

E2PL: Effective and Efficient Prompt Learning for Incomplete Multi-view Multi-Label Class Incremental Learning

Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously emerging classes, which pose significant obstacles to robust learning. Prevailing methods are ill-equipped for this reality, as they either lack adaptability to new classes or incur exponential parameter growth when handling all possible missing-view patterns, severely limiting their scalability in web environments. To systematically address this gap, we formally introduce a novel task, termed \emph{incomplete multi-view multi-label class incremental learning} (IMvMLCIL), which requires models to simultaneously address heterogeneous missing views and dynamic class expansion. To tackle this task, we propose \textsf{E2PL}, an Effective and Efficient Prompt Learning framework for IMvMLCIL. \textsf{E2PL} unifies two novel prompt designs: \emph{task-tailored prompts} for class-incremental adaptation and \emph{missing-aware prompts} for the flexible integration of arbitrary view-missing scenarios. To fundamentally address the exponential parameter explosion inherent in missing-aware prompts, we devise an \emph{efficient prototype tensorization} module, which leverages atomic tensor decomposition to elegantly reduce the prompt parameter complexity from exponential to linear w.r.t. the number of views. We further incorporate a \emph{dynamic contrastive learning} strategy explicitly model the complex dependencies among diverse missing-view patterns, thus enhancing the model's robustness. Extensive experiments on three benchmarks demonstrate that \textsf{E2PL} consistently outperforms state-of-the-art methods in both effectiveness and efficiency. The codes and datasets are available at https://anonymous.4open.science/r/code-for-E2PL.

cs.LG↗
arXiv2026

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become a core technology for tasks such as question-answering (QA) and content generation. RAG poisoning is an attack method to induce LLMs to generate the attacker's expected text by injecting poisoned documents into the database of RAG systems. Existing research can be broadly divided into two classes: white-box methods and black-box methods. White-box methods utilize gradient information to optimize poisoned documents, and black-box methods use a pre-trained LLM to generate them. However, existing white-box methods require knowledge of the RAG system's internal composition and implementation details, whereas black-box methods are unable to utilize interactive information. In this work, we propose the RIPRAG attack framework, an end-to-end attack pipeline that treats the target RAG system as a black box and leverages our proposed Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents. We designed two kinds of rewards: similarity reward and attack reward. Experimental results demonstrate that this method can effectively execute poisoning attacks against most complex RAG systems, achieving an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods. This highlights prevalent deficiencies in current defensive methods and provides critical insights for LLM security research.

cs.AI↗