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.

Augmenting Question Answering with A Hybrid RAG Approach

Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually relevant information, leading to incomplete or suboptimal answers. In this paper, we introduce Structured-Semantic RAG (SSRAG), a hybrid architecture that enhances QA quality by integrating query augmentation, agentic routing, and a structured retrieval mechanism combining vector and graph based techniques with context unification. By refining retrieval processes and improving contextual grounding, our approach improves both answer accuracy and informativeness. We conduct extensive evaluations on three popular QA datasets, TruthfulQA, SQuAD and WikiQA, across five Large Language Models (LLMs), demonstrating that our proposed approach consistently improves response quality over standard RAG implementations.

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use

Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (MCP) is considered a future trend. Current MCP evaluation sets suffer from issues such as reliance on external MCP services and a lack of difficulty awareness. To address these limitations, we propose MCPAgentBench, a benchmark based on real-world MCP definitions designed to evaluate the tool-use capabilities of agents. We construct a dataset containing authentic tasks and simulated MCP tools. The evaluation employs a dynamic sandbox environment that presents agents with candidate tool lists containing distractors, thereby testing their tool selection and discrimination abilities. Furthermore, we introduce comprehensive metrics to measure both task completion rates and execution efficiency. Experiments conducted on various latest mainstream Large Language Models reveal significant performance differences in handling complex, multi-step tool invocations. All code is open-source at Github.

In-Context Probing for Membership Inference in Fine-Tuned Language Models

Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sensitive data. While prior black-box MIA techniques rely on confidence scores or token likelihoods, these signals are often entangled with a sample's intrinsic properties - such as content difficulty or rarity - leading to poor generalization and low signal-to-noise ratios. In this paper, we propose ICP-MIA, a novel MIA framework grounded in the theory of training dynamics, particularly the phenomenon of diminishing returns during optimization. We introduce the Optimization Gap as a fundamental signal of membership: at convergence, member samples exhibit minimal remaining loss-reduction potential, while non-members retain significant potential for further optimization. To estimate this gap in a black-box setting, we propose In-Context Probing (ICP), a training-free method that simulates fine-tuning-like behavior via strategically constructed input contexts. We propose two probing strategies: reference-data-based (using semantically similar public samples) and self-perturbation (via masking or generation). Experiments on three tasks and multiple LLMs show that ICP-MIA significantly outperforms prior black-box MIAs, particularly at low false positive rates. We further analyze how reference data alignment, model type, PEFT configurations, and training schedules affect attack effectiveness. Our findings establish ICP-MIA as a practical and theoretically grounded framework for auditing privacy risks in deployed LLMs.

GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences

Exploring how genetic sequences shape phenotypes is a fundamental challenge in biology and a key step toward scalable, hypothesis-driven experimentation. The task is complicated by the large modality gap between sequences and phenotypes, as well as the pleiotropic nature of gene-phenotype relationships. Existing sequence-based efforts focus on the degree to which variants of specific genes alter a limited set of phenotypes, while general gene knockout induced phenotype abnormality prediction methods heavily rely on curated genetic information as inputs, which limits scalability and generalizability. As a result, the task of broadly predicting the presence of multiple phenotype abnormalities under gene knockout directly from gene sequences remains underexplored. We introduce GenePheno, the first interpretable multi-label prediction framework that predicts knockout induced phenotypic abnormalities from gene sequences. GenePheno employs a contrastive multi-label learning objective that captures inter-phenotype correlations, complemented by an exclusive regularization that enforces biological consistency. It further incorporates a gene function bottleneck layer, offering human interpretable concepts that reflect functional mechanisms behind phenotype formation. To support progress in this area, we curate four datasets with canonical gene sequences as input and multi-label phenotypic abnormalities induced by gene knockouts as targets. Across these datasets, GenePheno achieves state-of-the-art gene-centric $F_{\text{max}}$ and phenotype-centric AUC, and case studies demonstrate its ability to reveal gene functional mechanisms.

SEDM: Scalable Self-Evolving Distributed Memory for Agents

Long-term multi-agent systems inevitably generate vast amounts of trajectories and historical interactions, which makes efficient memory management essential for both performance and scalability. Existing methods typically depend on vector retrieval and hierarchical storage, yet they are prone to noise accumulation, uncontrolled memory expansion, and limited generalization across domains. To address these challenges, we present SEDM, Self-Evolving Distributed Memory, a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component. SEDM integrates verifiable write admission based on reproducible replay, a self-scheduling memory controller that dynamically ranks and consolidates entries according to empirical utility, and cross-domain knowledge diffusion that abstracts reusable insights to support transfer across heterogeneous tasks. Evaluations on benchmark datasets demonstrate that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines, and further enables knowledge distilled from fact verification to enhance multi-hop reasoning. The results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration. The code will be released in the later stage of this project.

EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning

Frame-based cameras with extended exposure times often produce perceptible visual blurring and information loss between frames, significantly degrading video quality. To address this challenge, we introduce EVDI++, a unified self-supervised framework for Event-based Video Deblurring and Interpolation that leverages the high temporal resolution of event cameras to mitigate motion blur and enable intermediate frame prediction. Specifically, the Learnable Double Integral (LDI) network is designed to estimate the mapping relation between reference frames and sharp latent images. Then, we refine the coarse results and optimize overall training efficiency by introducing a learning-based division reconstruction module, enabling images to be converted with varying exposure intervals. We devise an adaptive parameter-free fusion strategy to obtain the final results, utilizing the confidence embedded in the LDI outputs of concurrent events. A self-supervised learning framework is proposed to enable network training with real-world blurry videos and events by exploring the mutual constraints among blurry frames, latent images, and event streams. We further construct a dataset with real-world blurry images and events using a DAVIS346c camera, demonstrating the generalizability of the proposed EVDI++ in real-world scenarios. Extensive experiments on both synthetic and real-world datasets show that our method achieves state-of-the-art performance in video deblurring and interpolation tasks.

Undress to Redress: A Training-Free Framework for Virtual Try-On

Virtual try-on (VTON) is a crucial task for enhancing user experience in online shopping by generating realistic garment previews on personal photos. Although existing methods have achieved impressive results, they struggle with long-sleeve-to-short-sleeve conversions-a common and practical scenario-often producing unrealistic outputs when exposed skin is underrepresented in the original image. We argue that this challenge arises from the ''majority'' completion rule in current VTON models, which leads to inaccurate skin restoration in such cases. To address this, we propose UR-VTON (Undress-Redress Virtual Try-ON), a novel, training-free framework that can be seamlessly integrated with any existing VTON method. UR-VTON introduces an ''undress-to-redress'' mechanism: it first reveals the user's torso by virtually ''undressing,'' then applies the target short-sleeve garment, effectively decomposing the conversion into two more manageable steps. Additionally, we incorporate Dynamic Classifier-Free Guidance scheduling to balance diversity and image quality during DDPM sampling, and employ Structural Refiner to enhance detail fidelity using high-frequency cues. Finally, we present LS-TON, a new benchmark for long-sleeve-to-short-sleeve try-on. Extensive experiments demonstrate that UR-VTON outperforms state-of-the-art methods in both detail preservation and image quality. Code will be released upon acceptance.

SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios

Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model parameters by a global mask, are expected to protect privacy with reduced overhead and easy adaptation. However, in cross-device scenarios with heterogeneous data and system capabilities, traditional Selective HE methods deteriorate client straggling, and suffer from degraded HE overhead reduction performance. Accordingly, we propose SenseCrypt, a Sensitivity-guided selective Homomorphic EnCryption framework, to adaptively balance security and HE overhead per cross-device FL client. Given the observation that model parameter sensitivity is effective for measuring clients' data distribution similarity, we first design a privacy-preserving method to respectively cluster the clients with similar data distributions. Then, we develop a scoring mechanism to deduce the straggler-free ratio of model parameters that can be encrypted by each client per cluster. Finally, for each client, we formulate and solve a multi-objective model parameter selection optimization problem, which minimizes HE overhead while maximizing model security without causing straggling. Experiments demonstrate that SenseCrypt ensures security against the state-of-the-art inversion attacks, while achieving normal model accuracy as on IID data, and reducing training time by 58.4%-88.7% as compared to traditional HE methods.

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection

With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by general-purpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, an LLM-based framework for smart contract vulnerability detection. We first design targeted prompts to guide LLMs in identifying vulnerabilities and generating explanations, which serve as prediction features. Next, we apply prompt-tuning on CodeT5 and T5 to process contract code and explanations, enhancing task-specific performance. To combine the strengths of each approach, we introduce an Adaptive Mixture-of-Experts architecture. This dynamically adjusts feature weights via a Gating Network, which selects relevant features using TopK filtering and Softmax normalization, and incorporates a Multi-Head Self-Attention mechanism to enhance cross-feature relationships. This design enables effective integration of LLM predictions, explanation features, and code features through gradient optimization. The loss function jointly considers both independent feature performance and overall weighted predictions. Experiments show that SAEL outperforms existing methods across various vulnerabilities.