Yiran Zhang

Yiran Zhang, Mingyang Lin, Mark Dras et al.

Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VISTA, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VISTA allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model's step-by-step logical path. By providing a unified and interactive framework, VISTA significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models.

Yihao Ding, Yiran Zhang, Chris Gonzalez et al.

Geochemical anomaly detection plays a critical role in mineral exploration as deviations from regional geochemical baselines may indicate mineralization. Existing studies suffer from two key limitations: (1) single region scenarios which limit model generalizability; (2) proprietary datasets, which makes result reproduction unattainable. In this work, we introduce \textbf{GeoChemAD}, an open-source benchmark dataset compiled from government-led geological surveys, covering multiple regions, sampling sources, and target elements. The dataset comprises eight subsets representing diverse spatial scales and sampling conditions. To establish strong baselines, we reproduce and benchmark a range of unsupervised anomaly detection methods, including statistical models, generative and transformer-based approaches. Furthermore, we propose \textbf{GeoChemFormer}, a transformer-based framework that leverages self-supervised pretraining to learn target-element-aware geochemical representations for spatial samples. Extensive experiments demonstrate that GeoChemFormer consistently achieves superior and robust performance across all eight subsets, outperforming existing unsupervised methods in both anomaly detection accuracy and generalization capability. The proposed dataset and framework provide a foundation for reproducible research and future development in this direction.

Hanbo Huang, Yiran Zhang, Hao Zheng et al.

Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations are not sufficiently adversarial, obscuring critical vulnerabilities and overstating the security. To address this, we introduce the adaptive robustness radius, a formal metric that quantifies the worst-case resilience of watermarks against adaptive adversaries. By lifting the paraphrase space into a KL-divergence ball, we approximate this radius and theoretically demonstrate that optimizing the attack context and model parameters can significantly reduce the approximate radius, making watermarks highly vulnerable to paraphrase attacks. Leveraging this insight, we propose RLCracker, a reinforcement learning (RL)-based adaptive attack that erases watermark signals with limited watermarked examples and limited access to the detector. Despite weak supervision, it empowers a 3B model to achieve 98.5% removal success with minimal semantic shift on 1,500-token Unigram-marked texts after training on only 100 short samples. This performance dramatically exceeds 6.75% by GPT-4o and generalizes across five model sizes over ten watermarking schemes. Our code is available at https://github.com/OTT0-OTO/RLCracker.

Ruiyin Li, Yiran Zhang, Xiyu Zhou et al.

Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requirements. Traditionally, this process has been time-consuming, labor-intensive, and heavily reliant on architects, often resulting in limited exploration of alternative architectural decompositions and styles, especially under the pressures of agile development. While LLM-based agents have shown promising performance across various software engineering tasks, their application to architecture design remains relatively scarce and requires systematic exploration. To address these challenges, we proposed MAAD (Multi-Agent Architecture Design), a knowledge-driven framework that orchestrates four specialized agents (i.e., Analyst, Modeler, Designer and Evaluator) to autonomously and collaboratively transform requirements specifications into comprehensive, multi-view architectural blueprints with quality attribute assessments. MAAD incorporates RAG to inject recognized architectural standards and patterns into the workflow and leverages a hierarchical memory mechanism that captures design history for iterative refinement. We evaluated MAAD through comparative experiments against MetaGPT, using quantitative architecture-level metrics across 10 case studies and qualitative feedback from industry architects on 10 real-world specifications. Results show that MAAD generates more complete, modular, and traceable architectures than the baseline, and its dedicated Evaluator agent autonomously produces structured quality evaluation reports that significantly reduce manual validation efforts. Furthermore, we found that the quality of the generated architecture heavily depends on the underlying LLM's reasoning capacity, with GPT-5.2 and Qwen3.5 outperforming other models across most evaluation settings.

Usman Naseem, Robert Geislinger, Juan Ren et al.

We present SemEval-2026 Task 9, a shared task on online polarization detection, covering 22 languages and comprising over 110K annotated instances. Each data instance is multi-labeled with the presence of polarization, polarization type, and polarization manifestation. Participants were asked to predict labels in three sub-tasks: (1) detecting the presence of polarization, (2) identifying the type of polarization, and (3) recognizing the polarization manifestation. The three tasks attracted over 1,000 participants worldwide and more than 10k submission on Codabench. We received final submissions from 67 teams and 73 system description papers. We report the baseline results and analyze the performance of the best-performing systems, highlighting the most common approaches and the most effective methods across different subtasks and languages. The dataset of this task is publicly available.

Yanzhou Li, Yiran Zhang, Xiaoyu Zhang et al.

Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior. However, existing skill construction and maintenance methods often rely on fixed prompts and heuristic update rules, leaving it unclear how knowledge should be selected, abstracted, and maintained to best serve downstream agents. We propose CODESKILL, an LLM-based framework that reformulates skill extraction and skill-bank maintenance as a learnable management policy. CODESKILL extracts multi-granularity procedural skills from coding-agent trajectories, evolves skills with new experience, and maintains a compact skill bank for future task solving. We train CODESKILL with reinforcement learning, using a hybrid reward that combines dense rubric-based skill-quality feedback with sparse verifiable execution feedback from the frozen downstream agent. Experiments on EnvBench, SWE-Bench Verified, and Terminal-Bench 2 show that CODESKILL improves average pass rate by 9.69 over the no-skill baseline and by 4.01 over the strongest prompt-based or memory baseline, while maintaining the skill bank at a stable size during iterative construction.

Yiran Zhang, Jincheng Hu, Mark Dras et al.

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift, hallucination, overconfidence, and memory decay. Current approaches typically append full conversational histories, causing unbounded context growth, higher computational costs, and degraded reasoning efficiency. We introduce CogMem, a cognitively inspired, memory-augmented LLM architecture that supports sustained iterative reasoning through structured, persistent memory. CogMem incorporates three layers: a Long-Term Memory (LTM) that consolidates cross-session reasoning strategies; a Direct Access (DA) memory that maintains session-level notes and retrieves relevant long-term memories; and a Focus of Attention (FoA) mechanism that dynamically reconstructs concise, task-relevant context at each turn. Experiments on TurnBench show that this layered design mitigates reasoning failures, controls context growth, and improves consistency across extended reasoning chains, moving toward more reliable, human-like reasoning in LLMs.

Jia Li, Ruiqi Bai, Yangkang Luo et al.

Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although achieving improvements, existing approaches focus on designing reasoning strategies or post-refinement methods to enhance code generation performance. Despite their differences, all these methods share a common assumption: the LLM can correctly understand the given requirement. However, this assumption does not always hold. To fill this gap, we propose REA-Coder, a requirement alignment approach to enhance the code generation performance of LLMs. REA-Coder involves first identifying the requirement content that does not align with LLMs and aligning the requirements. Then, based on the aligned requirements, LLMs generate code and further verify whether the generated code aligns with the requirements, iterating this process of requirement alignment and code generation until generating correct code or achieving the maximum number of iterations. Experimental results show that REA-Coder outperforms all advanced baselines on four LLMs across five programming benchmarks. Concretely, REA-Coder achieves average improvements of 7.93%, 30.25%, 26.75%, 8.59%, and 8.64% on the five benchmark datasets, demonstrating the effectiveness of requirement alignment for improving the code generation performance of LLMs.

Dian Jiao, Jiaxin Duan, Shuai Zhao et al.

Recent achievements of vision-language models in end-to-end OCR point to a new avenue for low-loss compression of textual information. This motivates earlier works that render the Transformer's input into images for prefilling, which effectively reduces the number of tokens through visual encoding, thereby alleviating the quadratically increased Attention computations. However, this partial compression fails to save computational or memory costs at token-by-token inference. In this paper, we investigate global context compression, which saves tokens at both prefilling and inference stages. Consequently, we propose VIST2, a novel Transformer that interleaves input text chunks alongside their visual encoding, while depending exclusively on visual tokens in the pre-context to predict the next text token distribution. Around this idea, we render text chunks into sketch images and train VIST2 in multiple stages, starting from curriculum-scheduled pretraining for optical language modeling, followed by modal-interleaved instruction tuning. We conduct extensive experiments using VIST2 families scaled from 0.6B to 8B to explore the training recipe and hyperparameters. With a 4$\times$ compression ratio, the resulting models demonstrate significant superiority over baselines on long writing tasks, achieving, on average, a 3$\times$ speedup in first-token generation, 77% reduction in memory usage, and 74% reduction in FLOPS. Our codes and datasets will be public to support further studies.

Yiran Zhang, Xingpeng Sun, Aniket Bera

Natural walking enhances immersion in virtual environments (VEs), but physical space limitations and obstacles hinder exploration, especially in large virtual scenes. Redirected Walking (RDW) techniques mitigate this by subtly manipulating the virtual camera to guide users away from physical collisions within pre-defined VEs. However, RDW efficacy diminishes significantly when substantial geometric divergence exists between the physical and virtual environments, leading to unavoidable collisions. Existing scene generation methods primarily focus on object relationships or layout aesthetics, often neglecting the crucial aspect of physical compatibility required for effective RDW. To address this, we introduce HCVR (High Compatibility Virtual Reality Environment Generation), a novel framework that generates virtual scenes inherently optimized for alignment-based RDW controllers. HCVR first employs ENI++, a novel, boundary-sensitive metric to evaluate the incompatibility between physical and virtual spaces by comparing rotation-sensitive visibility polygons. Guided by the ENI++ compatibility map and user prompts, HCVR utilizes a Large Language Model (LLM) for context-aware 3D asset retrieval and initial layout generation. The framework then strategically adjusts object selection, scaling, and placement to maximize coverage of virtually incompatible regions, effectively guiding users towards RDW-feasible paths. User studies evaluating physical collisions and layout quality demonstrate HCVR's effectiveness with HCVR-generated scenes, resulting in 22.78 times fewer physical collisions and received 35.89\% less on ENI++ score compared to LLM-based generation with RDW, while also receiving 12.5\% higher scores on user feedback to layout design.

Doudou Zhou, Yiran Zhang, Dian Jin et al.

Clinical decision-making often involves selecting tests that are costly, invasive, or time-consuming, motivating individualized, sequential strategies for what to measure and when to stop ascertaining. We study the problem of learning cost-optimal sequential decision policies from retrospective data, where test availability depends on prior results, inducing informative missingness. Under a sequential missing-at-random mechanism, we develop a doubly robust Q-learning framework for estimating optimal policies. The method introduces path-specific inverse probability weights that account for heterogeneous test trajectories and satisfy a normalization property conditional on the observed history. By combining these weights with auxiliary contrast models, we construct orthogonal pseudo-outcomes that enable unbiased policy learning when either the acquisition model or the contrast model is correctly specified. We establish oracle inequalities for the stage-wise contrast estimators, along with convergence rates, regret bounds, and misclassification rates for the learned policy. Simulations demonstrate improved cost-adjusted performance over weighted and complete-case baselines, and an application to a prostate cancer cohort study illustrates how the method reduces testing cost without compromising predictive accuracy.

Hongyu Liang, Yuting Zheng, Yihan Li et al.

As large language models (LLMs) continue to advance, their deployment often involves fine-tuning to enhance performance on specific downstream tasks. However, this customization is sometimes accompanied by misleading claims about the origins, raising significant concerns about transparency and trust within the open-source community. Existing model verification techniques typically assess functional, representational, and weight similarities. However, these approaches often struggle against obfuscation techniques, such as permutations and scaling transformations. To address this limitation, we propose a novel detection method Origin-Tracer that rigorously determines whether a model has been fine-tuned from a specified base model. This method includes the ability to extract the LoRA rank utilized during the fine-tuning process, providing a more robust verification framework. This framework is the first to provide a formalized approach specifically aimed at pinpointing the sources of model fine-tuning. We empirically validated our method on thirty-one diverse open-source models under conditions that simulate real-world obfuscation scenarios. We empirically analyze the effectiveness of our framework and finally, discuss its limitations. The results demonstrate the effectiveness of our approach and indicate its potential to establish new benchmarks for model verification.

Liting Huang, Zhihao Zhang, Yiran Zhang et al.

The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The machine-generated content is a double-edged sword. On one hand, it can benefit the society when used appropriately. On the other hand, it may mislead people, posing threats to the society, especially when mixed together with natural content created by humans. Hence, there is an urgent need to develop effective methods to detect machine-generated content. However, the lack of aligned multimodal datasets inhibited the development of such methods, particularly in triple-modality settings (e.g., text, image, and voice). In this paper, we introduce RU-AI, a new large-scale multimodal dataset for robust and effective detection of machine-generated content in text, image and voice. Our dataset is constructed on the basis of three large publicly available datasets: Flickr8K, COCO and Places205, by adding their corresponding AI duplicates, resulting in a total of 1,475,370 instances. In addition, we created an additional noise variant of the dataset for testing the robustness of detection models. We conducted extensive experiments with the current SOTA detection methods on our dataset. The results reveal that existing models still struggle to achieve accurate and robust detection on our dataset. We hope that this new data set can promote research in the field of machine-generated content detection, fostering the responsible use of generative AI. The source code and datasets are available at https://github.com/ZhihaoZhang97/RU-AI.

Xuan Gong, Hanbo Huang, Hao Zheng et al.

Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train policies for stronger grounding, but where to intervene relies on perception heuristics rather than principled gain analysis, and how local visual influence propagates remains implicit. We study this problem from an information-theoretic standpoint and derive a lower bound on the downstream visual gain of a one-step intervention, which suggests two factors: local branching room (token entropy) and downstream visual propagation potential (suffix divergence from a vision-marginalized reference). Guided by this analysis, we propose reflection-anchor policy optimization (RAPO), a GRPO-based policy optimization method that selects high-entropy reflection anchors and optimizes a chain-masked finite-window KL surrogate for downstream visual dependence. Experiments on reasoning-intensive and general-domain benchmarks show that RAPO delivers substantial gains over strong baselines across multiple LVLM backbones. Mechanism analyses further indicate that reflection anchors are enriched for visually sensitive decision points and that RAPO increases contrastive visual-dependence signals along generated trajectories.

Hanbo Huang, Xuan Gong, Yiran Zhang et al.

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand extensive datasets and white-box access to algorithmic internals, limiting their practical applicability. In this paper, we study watermark resilience against spoofing fundamentally from a distributional perspective. We first establish a \textit{local capacity bottleneck}, which theoretically characterizes the probability mass that can be reallocated under KL-bounded local updates while preserving semantic fidelity. Building on this, we propose RLSpoofer, a reinforcement learning-based black-box spoofing attack that requires only 100 human-watermarked paraphrase training pairs and zero access to the watermarking internals or detectors. Despite weak supervision, it empowers a 4B model to achieve a 62.0\% spoof success rate with minimal semantic shift on PF-marked texts, dwarfing the 6\% of baseline models trained on up to 10,000 samples. Our findings expose the fragile spoofing resistance of current LLM watermarking paradigms, providing a lightweight evaluation framework and stressing the urgent need for more robust schemes.

Jia Li, Hongyi Deng, Yiran Zhang et al.

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and EvoCodeBench have been created to evaluate LLMs by requiring them to generate code from natural language requirements. However, in enterprise applications and team development, developers typically write code based on structured designs or specifications rather than raw natural language descriptions. This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate software development tasks. To address this gap, we propose RealBench, a repository-level code generation benchmark aligned with real-world industry software development practices. Each example includes both natural language requirements and UML diagrams as system design, matching how developers typically receive specifications. Based on the constructed benchmarks, we conduct a systematic evaluation of advanced LLMs' code generation capabilities when provided with structured system designs. The experimental results reveal key insights in current LLMs' capabilities for repo-level code generation aligned with real-world software development practices. First, we notice that regarding repo-level code generation, LLMs show much worse performance and there are significant performance gaps among LLMs. Second, LLMs are good at finding and creating modules defined in UML diagrams, but the quality of generated modules is often poor due to grammar and logic errors. Third, generating the entire repository at once is the best generation strategy on smaller repositories, while generating a complex repository with the module-by-module strategy works better compared to other strategies.

Zeling Zhang, Dongqi Cai, Yiran Zhang et al. · cambridge

Communication overhead is a significant bottleneck in federated learning (FL), which has been exaggerated with the increasing size of AI models. In this paper, we propose FedRDMA, a communication-efficient cross-silo FL system that integrates RDMA into the FL communication protocol. To overcome the limitations of RDMA in wide-area networks (WANs), FedRDMA divides the updated model into chunks and designs a series of optimization techniques to improve the efficiency and robustness of RDMA-based communication. We implement FedRDMA atop the industrial federated learning framework and evaluate it on a real-world cross-silo FL scenario. The experimental results show that \sys can achieve up to 3.8$\times$ speedup in communication efficiency compared to traditional TCP/IP-based FL systems.

Weisong Sun, Yiran Zhang, Jie Zhu et al.

Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce developers' workload, researchers has proposed various automated code summarization (ACS) techniques to automatically generate comments/summaries for given code units. However, these ACS techniques primarily focus on generating summaries for code units at the method level. There is a significant lack of research on summarizing higher-level code units, such as file-level and module-level code units, despite the fact that summaries of these higher-level code units are highly useful for quickly gaining a macro-level understanding of software components and architecture. To fill this gap, in this paper, we conduct a systematic study on how to use LLMs for commenting higher-level code units, including file level and module level. These higher-level units are significantly larger than method-level ones, which poses challenges in handling long code inputs within LLM constraints and maintaining efficiency. To address these issues, we explore various summarization strategies for ACS of higher-level code units, which can be divided into three types: full code summarization, reduced code summarization, and hierarchical code summarization. The experimental results suggest that for summarizing file-level code units, using the full code is the most effective approach, with reduced code serving as a cost-efficient alternative. However, for summarizing module-level code units, hierarchical code summarization becomes the most promising strategy. In addition, inspired by the research on method-level ACS, we also investigate using the LLM as an evaluator to evaluate the quality of summaries of higher-level code units. The experimental results demonstrate that the LLM's evaluation results strongly correlate with human evaluations.

Yiran Zhang, Mo Wang, Xiaoyang Li et al.

Despite impressive advances in large language models (LLMs), existing benchmarks often focus on single-turn or single-step tasks, failing to capture the kind of iterative reasoning required in real-world settings. To address this limitation, we introduce TurnBench, a novel benchmark that evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by a "Turing Machine Board Game." In each episode, a model must uncover hidden logical or arithmetic rules by making sequential guesses, receiving structured feedback, and integrating clues across multiple rounds. This dynamic setup requires models to reason over time, adapt based on past information, and maintain consistency across steps-capabilities underexplored in current benchmarks. TurnBench includes two modes: Classic, which tests standard reasoning, and Nightmare, which introduces increased complexity and requires robust inferential chains. To support fine-grained analysis, we provide ground-truth annotations for intermediate reasoning steps. Our evaluation of state-of-the-art LLMs reveals significant gaps: the best model achieves 81.5% accuracy in Classic mode, but performance drops to 17.8% in Nightmare mode. In contrast, human participants achieve 100% in both, underscoring the challenge TurnBench poses to current models. By incorporating feedback loops and hiding task rules, TurnBench reduces contamination risks and provides a rigorous testbed for diagnosing and advancing multi-step, multi-turn reasoning in LLMs.

Zhihao Zhang, Feiqi Cao, Yingbin Mo et al.

The dynamic nature of esports makes the situation relatively complicated for average viewers. Esports broadcasting involves game expert casters, but the caster-dependent game commentary is not enough to fully understand the game situation. It will be richer by including diverse multimodal esports information, including audiences' talks/emotions, game audio, and game match event information. This paper introduces GAME-MUG, a new multimodal game situation understanding and audience-engaged commentary generation dataset and its strong baseline. Our dataset is collected from 2020-2022 LOL game live streams from YouTube and Twitch, and includes multimodal esports game information, including text, audio, and time-series event logs, for detecting the game situation. In addition, we also propose a new audience conversation augmented commentary dataset by covering the game situation and audience conversation understanding, and introducing a robust joint multimodal dual learning model as a baseline. We examine the model's game situation/event understanding ability and commentary generation capability to show the effectiveness of the multimodal aspects coverage and the joint integration learning approach.

Yiran Zhang, Weihang Xu, Mo Zhou et al.

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functions. Despite its empirical success, the theoretical understanding of the optimization behavior of score matching, particularly in over-parameterized regimes, remains limited. In this work, we study gradient descent for training over-parameterized models to learn a single Gaussian distribution. Specifically, we use a student model with $n$ learnable parameters and train it on data generated from a single ground-truth Gaussian using the population score matching objective. We analyze the optimization dynamics under multiple regimes. When the noise scale is sufficiently large, we prove a global convergence result for gradient descent. In the low-noise regime, we identify the existence of a stationary point, highlighting the difficulty of proving global convergence in this case. Nevertheless, we show convergence under certain initialization conditions: when the parameters are initialized to be exponentially small, gradient descent ensures convergence of all parameters to the ground truth. We further prove that without the exponentially small initialization, the parameters may not converge to the ground truth. Finally, we consider the case where parameters are randomly initialized from a Gaussian distribution far from the ground truth. We prove that, with high probability, only one parameter converges while the others diverge, yet the loss still converges to zero with a $1/τ$ rate, where $τ$ is the number of iterations. We also establish a nearly matching lower bound on the convergence rate in this regime. This is the first work to establish global convergence guarantees for Gaussian mixtures with at least three components under the score matching framework.

Yanzhou Li, Tianlin Li, Yiran Zhang et al.

Large Language Models (LLMs) are increasingly used for function completion in repository-scale codebases. Prior studies demonstrate that when explicit instructions--such as docstrings--are provided, these models can generate highly accurate implementations. However, in real-world repositories, such annotations are frequently absent, and performance drops substantially without them. To address this gap, we frame the task as a three-stage process. The first stage focuses on intent inference, where the model analyzes the code preceding the target function to uncover cues about the desired functionality. Such preceding context often encodes subtle but critical information, and we design a reasoning-based prompting framework to guide the LLM through step-by-step extraction and synthesis of these signals before any code is generated. The second stage introduces an optional interactive refinement mechanism to handle cases where preceding context alone is insufficient for intent recovery. In this stage, the model proposes a small set of candidate intentions, enabling the developer to select or edit them so that the inferred intent closely matches the actual requirement. Finally, in the third stage, the LLM generates the target function conditioned on the finalized intent. To support this pipeline, we curate a dataset of 40,000 examples annotated with intermediate reasoning traces and corresponding docstrings. Extensive experiments on DevEval and ComplexCodeEval show that our approach consistently boosts multiple LLMs, achieving over 20\% relative gains in both reference-based and execution-based metrics, with the interactive refinement stage delivering additional improvements beyond these gains.

Ruiyin Li, Yiran Zhang, Xiyu Zhou et al.

Software architecture design is a critical, yet inherently complex and knowledge-intensive phase of software development. It requires deep domain expertise, development experience, architectural knowledge, careful trade-offs among competing quality attributes, and the ability to adapt to evolving requirements. Traditionally, this process is time-consuming and labor-intensive, and relies heavily on architects, often resulting in limited design alternatives, especially under the pressures of agile development. While Large Language Model (LLM)-based agents have shown promising performance across various SE tasks, their application to architecture design remains relatively scarce and requires more exploration, particularly in light of diverse domain knowledge and complex decision-making. To address the challenges, we proposed MAAD (Multi-Agent Architecture Design), an automated framework that employs a knowledge-driven Multi-Agent System (MAS) for architecture design. MAAD orchestrates four specialized agents (i.e., Analyst, Modeler, Designer and Evaluator) to collaboratively interpret requirements specifications and produce architectural blueprints enriched with quality attributes-based evaluation reports. We then evaluated MAAD through a case study and comparative experiments against MetaGPT, a state-of-the-art MAS baseline. Our results show that MAAD's superiority lies in generating comprehensive architectural components and delivering insightful and structured architecture evaluation reports. Feedback from industrial architects across 11 requirements specifications further reinforces MAAD's practical usability. We finally explored the performance of the MAAD framework with three LLMs (GPT-4o, DeepSeek-R1, and Llama 3.3) and found that GPT-4o exhibits better performance in producing architecture design, emphasizing the importance of LLM selection in MAS-driven architecture design.

Jixiang Hong, Yiran Zhang, Guanzhong Wang et al.

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are naturally inverse dual tasks, we propose \textbf{SUDER} (\textbf{S}elf-improving \textbf{U}nified LMMs with \textbf{D}ual s\textbf{E}lf-\textbf{R}ewards), a framework reinforcing the understanding and generation capabilities of LMMs with a self-supervised dual reward mechanism. SUDER leverages the inherent duality between understanding and generation tasks to provide self-supervised optimization signals for each other. Specifically, we sample multiple outputs for a given input in one task domain, then reverse the input-output pairs to compute the dual likelihood within the model as self-rewards for optimization. Extensive experimental results on visual understanding and generation benchmarks demonstrate that our method can effectively enhance the performance of the model without any external supervision, especially achieving remarkable improvements in text-to-image tasks.

Zhihao Zhang, Yiran Zhang, Xiyue Zhou et al.

Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health measures. Recent advancements in generative AI, capable of producing realistic, human like text and images, have significantly accelerated the spread and expanded the reach of health misinformation, resulting in an alarming surge in its dissemination. To combat the infodemics, most existing work has focused on developing misinformation datasets from social media and fact checking platforms, but has faced limitations in topical coverage, inclusion of AI generation, and accessibility of raw content. To address these issues, we present MM Health, a large scale multimodal misinformation dataset in the health domain consisting of 34,746 news article encompassing both textual and visual information. MM Health includes human-generated multimodal information (5,776 articles) and AI generated multimodal information (28,880 articles) from various SOTA generative AI models. Additionally, We benchmarked our dataset against three tasks (reliability checks, originality checks, and fine-grained AI detection) demonstrating that existing SOTA models struggle to accurately distinguish the reliability and origin of information. Our dataset aims to support the development of misinformation detection across various health scenarios, facilitating the detection of human and machine generated content at multimodal levels.

Peng Hang, Yiran Zhang, Chen Lv

In this paper, a human-like driving framework is designed for autonomous vehicles (AVs), which aims to make AVs better integrate into the transportation ecology of human driving and eliminate the misunderstanding and incompatibility of human drivers to autonomous driving. Based on the analysis of the real world INTERACTION dataset, a driving aggressiveness estimation model is established with the fuzzy inference approach. Then, a human-like driving model, which integrates the brain emotional learning circuit model (BELCM) with the two-point preview model, is designed. In the human-like lane-change decision-making algorithm, the cost function is designed comprehensively considering driving safety and travel efficiency. Based on the cost function and multi-constraint, the dynamic game algorithm is applied to modelling the interaction and decision making between AV and human driver. Additionally, to guarantee the lane-change safety of AVs, an artificial potential field model is built for collision risk assessment. Finally, the proposed algorithm is evaluated through human-in-the-loop experiments on a driving simulator, and the results demonstrated the feasibility and effectiveness of the proposed method.