arXiv subjects

Jianguo Zhang

Publications and source records attributed to Jianguo Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Test-Time Adaptation for LLM Agents via Environment Interaction

Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-training and test-time conditions. This challenge stems from two distinct failure modes: a syntactic misunderstanding of environment-specific components like observation formats, and a semantic misunderstanding of state-transition dynamics, which are only revealed at test time. To address these issues, we propose two distinct strategies for adapting LLM agents by leveraging environment-specific information from interaction that is available during deployment. First, an online syntactic alignment (SA) method parameterizes environmental nuances by learning a lightweight adaptation vector that biases the model's output distribution, enabling rapid alignment with an environment response format. Second, a deployment-time dynamics grounding (DG) method employs a persona-driven exploration phase to systematically probe and learn the environment's causal dynamics before task execution, equipping the agent with an in-context world model. We evaluate these strategies across diverse agentic benchmarks, including function calling and web navigation. Our empirical results show the effectiveness of both strategies across all benchmarks with minimal computational cost. We find that dynamics grounding is particularly effective in complex environments where unpredictable dynamics pose a major obstacle, demonstrating a robust path toward more generalizable and capable LLM-based agents. For example, on the WebArena multi-site split, this method increases the agent's success rate from 2% to 23%. We release our code.

cs.LG↗

arXiv2026

ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI

Brain age has become a prominent biomarker of brain health. Yet most prior work targets whole brain age (WBA), a coarse paradigm that struggles to support tasks such as disease characterization and research on development and aging patterns, because relevant changes are typically region-selective rather than brain-wide. Therefore, robust regional brain age (ReBA) estimation is critical, yet a widely generalizable model has yet to be established. In this paper, we propose the Regional Brain Age Prediction Network (ReBA-Pred-Net), a Teacher-Student framework designed for fine-grained brain age estimation. The Teacher produces soft ReBA to guide the Student to yield reliable ReBA estimates with a clinical-prior consistency constraint (regions within the same function should change similarly). For rigorous evaluation, we introduce two indirect metrics: Healthy Control Similarity (HCS), which assesses statistical consistency by testing whether regional brain-age-gap (ReBA minus chronological age) distributions align between training and unseen HC; and Neuro Disease Correlation (NDC), which assesses factual consistency by checking whether clinically confirmed patients show elevated brain-age-gap in disease-associated regions. Experiments across multiple backbones demonstrate the statistical and factual validity of our method.

cs.CV↗

arXiv2025

Experimental Demonstration and Transformation Mechanism of Quenchable Two-dimensional Diamond

Two-dimensional (2D) diamond has aroused tremendous interest in nanoelectronics and optoelectronics, owing to its superior properties and flexible characteristics compared to bulk diamond. Despite significant efforts, great challenges lie in the experimental synthesis and transformation conditions of 2D diamond. Herein, we have demonstrated the experimental preparation of high quality 2D diamond with controlled thickness and distinguished properties, realized by laser-heating few-layer graphene in diamond anvil cell. The quenched 2D diamond exhibited narrow T2g Raman peak (linewidth ~3.6 cm-1) and intense photoluminescence of SiV- (linewidth ~6.1 nm) and NV0 centers. In terms of transformation mechanism, atomic structures of hybrid phase interfaces suggested that the intermediate rhombohedral phase subtly mediate hexagonal graphite to cubic diamond transition. Furthermore, the tunable optical bandgap and thermal stability of 2D diamond sensitively depend on its sp3 concentration. We believe our results can shed light on the structural design and preparation of many carbon allotropes and further uncover the underlying transition mechanism.

cond-mat.mtrl-sci↗

arXiv2025

Enhancing Knowledge Transfer in Hyperspectral Image Classification via Cross-scene Knowledge Integration

Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spectral variations caused by different sensors and semantic inconsistencies across heterogeneous scenes. Existing methods are limited by transfer settings that assume homogeneous domains or heterogeneous scenarios with only co-occurring categories. When label spaces do not overlap, they further rely on complete source-domain coverage and therefore overlook critical target-private information. To overcome these limitations and enable knowledge transfer in fully heterogeneous settings, we propose Cross-scene Knowledge Integration (CKI), a framework that explicitly incorporates target-private knowledge during transfer. CKI includes: (1) Alignment of Spectral Characteristics (ASC) to reduce spectral discrepancies through domain-agnostic projection; (2) Cross-scene Knowledge Sharing Preference (CKSP), which resolves semantic mismatch via a Source Similarity Mechanism (SSM); and (3) Complementary Information Integration (CII) to maximize the use of target-specific complementary cues. Extensive experiments verify that CKI achieves state-of-the-art performance with strong stability across diverse cross-scene HSI scenarios.

cs.CV↗

arXiv2025

Video Understanding with Large Language Models: A Survey

With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding that harness the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (general, temporal, and spatiotemporal) reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into three main types: Video Analyzer x LLM, Video Embedder x LLM, and (Analyzer + Embedder) x LLM. Furthermore, we identify five sub-types based on the functions of LLMs in Vid-LLMs: LLM as Summarizer, LLM as Manager, LLM as Text Decoder, LLM as Regressor, and LLM as Hidden Layer. Furthermore, this survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at https://github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.

cs.CV↗

arXiv2025

TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing

Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes, typically addressing only one aspect - such as editing text content - thus limiting controllability and visual consistency. To overcome these limitations, we propose TripleFDS, a novel framework for STE with disentangled modular attributes, and an accompanying dataset called SCB Synthesis. SCB Synthesis provides robust training data for triple feature disentanglement by utilizing the "SCB Group", a novel construct that combines three attributes per image to generate diverse, disentangled training groups. Leveraging this construct as a basic training unit, TripleFDS first disentangles triple features, ensuring semantic accuracy through inter-group contrastive regularization and reducing redundancy through intra-sample multi-feature orthogonality. In the synthesis phase, TripleFDS performs feature remapping to prevent "shortcut" phenomena during reconstruction and mitigate potential feature leakage. Trained on 125,000 SCB Groups, TripleFDS achieves state-of-the-art image fidelity (SSIM of 44.54) and text accuracy (ACC of 93.58%) on the mainstream STE benchmarks. Besides superior performance, the more flexible editing of TripleFDS supports new operations such as style replacement and background transfer. Code: https://github.com/yusenbao01/TripleFDS

cs.CV↗

arXiv2025

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like LoCoBench~\cite{qiu2025locobench} assess long-context code understanding, they focus on single-turn evaluation and cannot capture the multi-turn interactive nature, tool usage patterns, and adaptive reasoning required by real-world coding agents. We introduce \textbf{LoCoBench-Agent}, a comprehensive evaluation framework specifically designed to assess LLM agents in realistic, long-context software engineering workflows. Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations, tool usage efficiency, error recovery, and architectural consistency across extended development sessions. We also introduce an evaluation methodology with 9 metrics across comprehension and efficiency dimensions. Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens, enabling precise assessment of long-context performance. Through systematic evaluation of state-of-the-art models, we reveal several key findings: (1) agents exhibit remarkable long-context robustness; (2) comprehension-efficiency trade-off exists with negative correlation, where thorough exploration increases comprehension but reduces efficiency; and (3) conversation efficiency varies dramatically across models, with strategic tool usage patterns differentiating high-performing agents. As the first long-context LLM agent benchmark for software engineering, LoCoBench-Agent establishes a rigorous foundation for measuring agent capabilities, identifying performance gaps, and advancing autonomous software development at scale.

cs.SE↗

arXiv2025

GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs

Graph neural networks (GNNs) on text--attributed graphs (TAGs) typically encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation. However, the representation spaces of modern PLMs are highly non--linear and geometrically structured, where textual embeddings reside on curved semantic manifolds rather than flat Euclidean spaces. Linear aggregation on such manifolds inevitably distorts geometry and causes semantic drift--a phenomenon where aggregated representations deviate from the intrinsic manifold, losing semantic fidelity and expressive power. To quantitatively investigate this problem, this work introduces a local PCA--based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure. Building upon these insights, we propose Geodesic Aggregation, a manifold--aware mechanism that aggregates neighbor information along geodesics via log--exp mappings on the unit sphere, ensuring that representations remain faithful to the semantic manifold during message passing. We further develop GeoGNN, a practical instantiation that integrates spherical attention with manifold interpolation. Extensive experiments across four benchmark datasets and multiple text encoders show that GeoGNN substantially mitigates semantic drift and consistently outperforms strong baselines, establishing the importance of manifold--aware aggregation in text--attributed graph learning.

cs.LG↗

arXiv2025

The 1st Solution for CARE Liver Task Challenge 2025: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation

Accurate liver segmentation from contrast-enhanced MRI is essential for diagnosis, treatment planning, and disease monitoring. However, it remains challenging due to limited annotated data, heterogeneous enhancement protocols, and significant domain shifts across scanners and institutions. Traditional image-to-image translation frameworks have made great progress in domain generalization, but their application is not straightforward. For example, Pix2Pix requires image registration, and cycle-GAN cannot be integrated seamlessly into segmentation pipelines. Meanwhile, these methods are originally used to deal with cross-modality scenarios, and often introduce structural distortions and suffer from unstable training, which may pose drawbacks in our single-modality scenario. To address these challenges, we propose CoSSeg-TTA, a compact segmentation framework for the GED4 (Gd-EOB-DTPA enhanced hepatobiliary phase MRI) modality built upon nnU-Netv2 and enhanced with a semi-supervised mean teacher scheme to exploit large amounts of unlabeled volumes. A domain adaptation module, incorporating a randomized histogram-based style appearance transfer function and a trainable contrast-aware network, enriches domain diversity and mitigates cross-center variability. Furthermore, a continual test-time adaptation strategy is employed to improve robustness during inference. Extensive experiments demonstrate that our framework consistently outperforms the nnU-Netv2 baseline, achieving superior Dice score and Hausdorff Distance while exhibiting strong generalization to unseen domains under low-annotation conditions.

cs.CV↗

arXiv2025

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning

Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks. The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools. For instance, in domains such as physics question answering, suitable and specialized tools are often missing. Recent work has explored automating tool creation by extracting reusable functions from Chain-of-Thought (CoT) reasoning traces; however, these approaches face a critical scalability bottleneck. As the number of generated tools grows, storing them in an unstructured collection leads to significant retrieval challenges, including an expanding search space and ambiguity between function-related tools. To address this, we propose a systematic approach to automatically refactor an unstructured collection of tools into a structured tool library. Our system first generates discrete, task-specific tools and clusters them into semantically coherent topics. Within each cluster, we introduce a multi-agent framework to consolidate scattered functionalities: a code agent refactors code to extract shared logic and creates versatile, aggregated tools, while a reviewing agent ensures that these aggregated tools maintain the complete functional capabilities of the original set. This process transforms numerous question-specific tools into a smaller set of powerful, aggregated tools without loss of functionality. Experimental results demonstrate that our approach significantly improves tool retrieval accuracy and overall reasoning performance across multiple reasoning tasks. Furthermore, our method shows enhanced scalability compared with baselines as the number of question-specific increases.

cs.CL↗

arXiv2025

Optimal Smooth Coverage Trajectory Planning for Quadrotors in Cluttered Environment

For typical applications of UAVs in power grid scenarios, we construct the problem as planning UAV trajectories for coverage in cluttered environments. In this paper, we propose an optimal smooth coverage trajectory planning algorithm. The algorithm consists of two stages. In the front-end, a Genetic Algorithm (GA) is employed to solve the Traveling Salesman Problem (TSP) for Points of Interest (POIs), generating an initial sequence of optimized visiting points. In the back-end, the sequence is further optimized by considering trajectory smoothness, time consumption, and obstacle avoidance. This is formulated as a nonlinear least squares problem and solved to produce a smooth coverage trajectory that satisfies these constraints. Numerical simulations validate the effectiveness of the proposed algorithm, ensuring UAVs can smoothly cover all POIs in cluttered environments.

cs.RO↗

arXiv2025

CoDA: Coding LM via Diffusion Adaptation

Diffusion language models promise bidirectional context and infilling capabilities that autoregressive coders lack, yet practical systems remain heavyweight. We introduce CoDA, a 1.7B-parameter diffusion coder trained on TPU with a fully open-source training pipeline. CoDA pairs large-scale diffusion pre-training with code-centric mid-training and instruction tuning, enabling confidence-guided sampling that keeps inference latency competitive. On Humaneval, MBPP, and EvalPlus, CoDA-1.7B-Instruct matches or surpasses diffusion models up to 7B parameters. Our release includes model checkpoints, evaluation harnesses, and TPU training pipelines to accelerate research on lightweight diffusion-based coding assistants.

cs.LG↗

arXiv2025

LATTE: Learning to Think with Vision Specialists

While open-source vision-language models perform well on simple question-answering, they still struggle with complex questions that require both perceptual and reasoning capabilities. We propose LATTE, a family of vision-language models that have LeArned to Think wiTh vision spEcialists. By offloading perception to state-of-the-art vision models, our approach enables vision-language models to focus solely on reasoning over high-quality perceptual information. To train LATTE, we synthesize and filter a large dataset of 293K multi-modal reasoning traces over perceptual outputs of vision specialists. LATTE trained on this data achieves significant 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities. Ablation studies reveal that the effectiveness of multi-modal reasoning traces depends on the data sources, formats, and quality of thoughts.

cs.CV↗

arXiv2025

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

The emergence of long-context language models with context windows extending to millions of tokens has created new opportunities for sophisticated code understanding and software development evaluation. We propose LoCoBench, a comprehensive benchmark specifically designed to evaluate long-context LLMs in realistic, complex software development scenarios. Unlike existing code evaluation benchmarks that focus on single-function completion or short-context tasks, LoCoBench addresses the critical evaluation gap for long-context capabilities that require understanding entire codebases, reasoning across multiple files, and maintaining architectural consistency across large-scale software systems. Our benchmark provides 8,000 evaluation scenarios systematically generated across 10 programming languages, with context lengths spanning 10K to 1M tokens, a 100x variation that enables precise assessment of long-context performance degradation in realistic software development settings. LoCoBench introduces 8 task categories that capture essential long-context capabilities: architectural understanding, cross-file refactoring, multi-session development, bug investigation, feature implementation, code comprehension, integration testing, and security analysis. Through a 5-phase pipeline, we create diverse, high-quality scenarios that challenge LLMs to reason about complex codebases at unprecedented scale. We introduce a comprehensive evaluation framework with 17 metrics across 4 dimensions, including 8 new evaluation metrics, combined in a LoCoBench Score (LCBS). Our evaluation of state-of-the-art long-context models reveals substantial performance gaps, demonstrating that long-context understanding in complex software development represents a significant unsolved challenge that demands more attention. LoCoBench is released at: https://github.com/SalesforceAIResearch/LoCoBench.

cs.SE↗

arXiv2025

A localization algebra approach to the Baum-Connes conjecture for extensions

For an extension $1\rightarrow N \rightarrow Γ\xrightarrow{q} Γ/ N \rightarrow 1$ of discrete countable groups, it is known that the Baum-Connes conjecture with coefficients holds for $Γ$ if it holds for $Γ/ N$ and $q^{-1}(F)$ for any finite subgroup $F$ of $Γ/ N$. In this paper, we employ a localization algebra approach to prove this result.

math.OA↗

arXiv2025

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI models to access and interpret a user's private data (e.g., conversation history, user-AI interactions, app usage) to understand personal details such as biographical information, preferences, and social connections. However, due to the sensitive nature of such data, there are no publicly available datasets that allow us to assess an AI model's ability to understand users through direct access to personal information. To address this gap, we introduce a synthetic data generation pipeline that creates diverse, realistic user profiles and private documents simulating human activities. Leveraging this synthetic data, we present PersonaBench, a benchmark designed to evaluate AI models' performance in understanding personal information derived from simulated private user data. We evaluate Retrieval-Augmented Generation (RAG) pipelines using questions directly related to a user's personal information, supported by the relevant private documents provided to the models. Our results reveal that current retrieval-augmented AI models struggle to answer private questions by extracting personal information from user documents, highlighting the need for improved methodologies to enhance personalization capabilities in AI.

cs.AI↗

arXiv2025

MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models

The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks and labor-intensive data collection, limiting practical assessment. We introduce MCPEval, an open-source Model Context Protocol (MCP)-based framework that automates end-to-end task generation and deep evaluation of LLM agents across diverse domains. MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines. Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance. We publicly release MCPEval https://github.com/SalesforceAIResearch/MCPEval to promote reproducible and standardized LLM agent evaluation.

cs.AI↗

arXiv2025

UserBench: An Interactive Gym Environment for User-Centric Agents

Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague, evolving, or indirectly expressed, remains underexplored. To address this gap, we introduce UserBench, a user-centric benchmark designed to evaluate agents in multi-turn, preference-driven interactions. UserBench features simulated users who start with underspecified goals and reveal preferences incrementally, requiring agents to proactively clarify intent and make grounded decisions with tools. Our evaluation of leading open- and closed-source LLMs reveals a significant disconnect between task completion and user alignment. For instance, models provide answers that fully align with all user intents only 20% of the time on average, and even the most advanced models uncover fewer than 30% of all user preferences through active interaction. These results highlight the challenges of building agents that are not just capable task executors, but true collaborative partners. UserBench offers an interactive environment to measure and advance this critical capability.

cs.AI↗