Searcharxiv⌕ Search

arXiv subjects

Zhiwei Yang

Publications and source records attributed to Zhiwei Yang.

At least 19 recordsLinked to original sources
arXiv2026

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement

Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on what experience to generate next, while paying less attention to when fresh experience should be introduced. Many also construct training targets through self-consistency or majority voting, making supervision depend on the model's own uncertain predictions. We address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable. A-RSI monitors reward variation and accuracy in training logs to refresh a task pool when its learning signal declines, without consulting validation or test scores. A static library of model-authored programs produces multimodal questions and derives their reference answers; we specify the task-generation contract, automatically verify chosen properties of the reward and refresh rules, and separately audit the generated answers. The training loop uses no external training examples or human-written answer labels. On the primary eleven-benchmark suite, A-RSI raises the performance average from 57.77 to 61.05 with 800 fresh tasks.

cs.AI↗
arXiv2026

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods usually incur substantial computational overhead due to per-question multi-rollout sampling and repeated per-token probability evaluation across rollouts. Furthermore, low-information or highly homogeneous trajectories can degrade downstream learning signal efficiency, hindering model optimization and limiting final performance. To address these issues, we propose FastRL, a novel plug-and-play reinforcement learning framework that simultaneously improves training efficiency and the effectiveness of policy learning. Specifically, 1) We introduce an advantage-aware pruning strategy to selectively preserve high-advantage trajectories while maximizing inter-trajectory gradient diversity. 2) Then, we design an adaptive rollout sampling mechanism to dynamically adjust the sampling scale across different training stages based on historical pruning distributions, balancing exploration adequacy and computational efficiency. Experiments demonstrate that FastRL can be seamlessly integrated into GRPO, DAPO, and GSPO variants, achieving an average 2.07$\times$ training speedup on Geometry3K and GeoQA8K-R1V, along with an approximately 1.64\% improvement in average accuracy on visual reasoning benchmarks. Source codes will be available at https://github.com/Nicozwy/FastRL.

cs.AI↗
arXiv2026

OmniStepBench: Deployment-Aware Agent Evaluation across Modalities and Task Complexity

As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to assess multimodal perception, multi-step execution, tool use, and artifact delivery. However, existing benchmarks are often tied to specific task types, execution environments, or scoring protocols, limiting their comparability, interpretability, and reliability for deployment decisions. We introduce \textbf{OmniStepBench}, a benchmark for deployment-aware agent evaluation across modalities and task complexity. Built on a shared OpenClaw execution environment, OmniStepBench organizes 233 tasks selected and adapted from 22 source benchmarks into a $2\times3$ workload matrix defined by input modality and execution form, and evaluates them under a unified contract-based protocol with evidence-based score auditing. We evaluate 30 commercial API models and 12 locally deployed open-weight models (42 models in total) over 9{,}218 applicable model--task runs, reporting accuracy and token consumption alongside reference costs for API models. Results show workload-dependent rankings, distinct accuracy--cost trade-offs between text and multimodal tasks, and competitive but weaker overall performance from local models. These findings support deployment decisions based on workload profiles, deployment mode, and accuracy--cost trade-offs rather than a single aggregate score.

cs.AI↗
arXiv2026

SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging

Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and online teaching practices. Recent work has explored large language models (LLMs) for this task, achieving promising performance. However, LLMs still struggle to select the correct concept from a large-scale candidate set due to the high dimensionality of the decision space. In this paper, we propose a novel three-stage Select-Reason-Judge (SRJudge) framework, which empowers LLMs with selective reasoning capability for fine-grained knowledge concept tagging. Specifically, the Selector in Stage 1 first narrows the candidate concepts to a top-K shortlist by fine-tuning a small language model (SLM), e.g., BERT, since the top-$K$ predictions hit the correct concept in most cases, thereby reducing the decision space of correct candidates. Next, the Stage 2 Reasoner employs a lightweight LLM for refined reasoning over the shortlisted candidates. It further integrates an improved reinforcement learning strategy with a dynamic task-specific reward function and a pruning mechanism to better align with human reasoning preferences. Finally, a larger LLM acts as a judger that evaluates the overall rationality of the reasoning process and its explanations to determine the final output. In addition, we construct two high-quality datasets for further validation, i.e., the biology dataset S_Bio and the physics dataset S_Phy. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines across benchmark datasets, verifying its effectiveness and superiority. Resources are available at: https://github.com/Nicozwy/SRJudge.

cs.CL↗
arXiv2026

Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models

Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often struggle with complex queries requiring fine-grained visual details or external knowledge. To acquire this missing evidence, agentic VLMs invoke tools such as image cropping, image search, and text search. However, existing training paradigms primarily evaluate tool-use based on final answer correctness, leaving evidence acquisition and utilization insufficiently supervised. This leads to two critical shortcomings: (i) models frequently issue redundant or off-target tool calls that fail to gather necessary evidence, and (ii) even when appropriate tools are called, models often fail to extract the necessary information from the resulting observations. To address these limitations, we introduce the NTEP (Necessary Tool-Evidence Path), a novel annotation scheme that explicitly specifies the essential external evidence and corresponding tool calls for each query. Building upon this, we propose NTEP-R (NTEP Reward), a supervision mechanism ensuring that each tool invocation strictly advances the reasoning process toward the final solution. Specifically, our approach rewards the agent for aligning its pre-call intent with a necessary evidence-seeking goal, and for ensuring the information summarized from the post-call observation aligns with the necessary evidence. Furthermore, we introduce a non-repeated-goal regularizer to penalize redundant calls that revisit satisfied NTEP goals. Extensive evaluations on seven image-grounded benchmarks demonstrate that our 8B-parameter instantiation, NTEP-8B, significantly improves both search-oriented accuracy and tool-use efficiency within a unified three-tool framework. These results highlight the critical value of fine-grained tool-evidence path supervision for training robust agentic VLMs.

cs.AI↗
arXiv2026

ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives

Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact, locally deployable language models are a practical alternative, but directly feeding them an entire long context remains costly, hard to inspect, and prone to missing sparse evidence. We present ClueWeaver, an evidence-aware dual-agent framework for long-narrative question answering with compact local models. A Finder identifies passages containing answer-critical clues through retrieval-guided segmentation, while an Interpreter derives the answer from the selected evidence, produces rationales with paragraph-ID citations, and applies an internal self-calibration pass for high-risk questions. Both agents are optimized with reward-guided reinforcement learning: Finder rewards emphasize evidence retention and faithful paragraph-ID references, and Interpreter rewards emphasize correctness, grounding, and concise explanations. This decomposition makes evidence selection and reasoning more inspectable than end-to-end prompting. Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end language models while providing evidence coverage and paragraph-referenced reasoning traces. Code is available at https://github.com/Ameame1/ClueWeaver.

cs.CL↗
arXiv2026

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model (LLM) agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing safeguards remain limited: generic guardrails do not model shell structure in sufficient detail, always-on LLM judges are relatively costly and variable, and shell parsers do not directly prevent harmful execution. We present CARE (Canonicalization, Attribution, and Resolution Engine), a shell-specific, static-first verifier for individual shell commands before execution. CARE canonicalizes generated commands into stable verification targets, derives deterministic evidence over syntax, command semantics, path context, and provenance-backed risk patterns, and escalates only underdetermined cases to an LLM judge. This design keeps the common case fast, reproducible, and auditable while reserving neural adjudication for borderline commands. On the balanced main split, CARE reaches 85.64% F1 with a 0.91% false-positive rate at 2.32 ms mean latency. When deployed in its static enforcement profile, CARE retains 84.99% F1 at 0.34 ms and reduces realised harm on RedCode-gen to 37.33%. Across external-generalization tests and controlled Docker-sandbox execution, these profiles expose a practical trade-off between benign recovery, false-positive burden, latency, and harm reduction. Overall, command-level shell mediation can reduce dispatch-boundary risk for LLM agents while preserving most benign workflows.

cs.CR↗
arXiv2026

MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing

Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural errors in these inputs can compromise downstream results and hinder manual inspection. LLM advances in computational chemistry offer paths beyond predictive screening toward fine-grained diagnosis with evidence-grounded explanations. However, two challenges remain: (i) limited fine-grained attribution: MOF-specific validators and machine-learning models scale detection but provide fixed checks, readiness scores, or coarse labels rather than evidence-grounded explanations; and (ii) unreliable CIF reasoning: direct LLM auditing is costly and unreliable because chemical evidence is implicit across atom-site records and requires geometric, connectivity, occupancy, and charge calculations. Both stem from weak coupling between chemical evidence and language-model explanation. We introduce MOF-Sleuth, a reinforcement-guided CIF auditing agent with two modules: a deterministic Forensic Lab and a Sleuth reasoning engine. The Lab derives composition, geometry, connectivity, occupancy, coordination, and charge evidence, and Sleuth uses this evidence to produce an evidence-grounded explanation, error types, and a binary decision. Reward-guided reinforcement learning (RL) turns tool measurements into chemical explanation-level supervision, rewarding not only the final answer but also cited chemical evidence and evidence-supported diagnoses. We introduce Chemically Grounded Diagnosis (Chem-GD), a metric that assesses whether a correct diagnosis is explained by factual, relevant CIF-derived evidence. Across four benchmarks, MOF-Sleuth establishes state-of-the-art performance among LLM-based approaches and MOF-specific machine-learning methods, demonstrating gains in detection, attribution, and grounded explanation quality.

cs.AI↗
arXiv2026

From physical surfaces to human-centric heat stress: LST and UTCI heat mapping reveals nonlinear effects of urban morphology

Heat exposure connects the built environment and public health, directly shaping the livability and sustainability of urban areas. Understanding the spatial heterogeneity of heat exposure and its drivers is vital for climate-adaptive urban planning. However, most planning-oriented studies rely on land surface temperature (LST), and whether LST adequately represents human heat exposure and how it differs from physiologically relevant heat stress remains insufficiently examined. Here, using Landsat-retrieved 30-m LST and GPU-accelerated 1-m universal thermal climate index (UTCI) in Singapore, this study establishes a comprehensive "Modeling-Comparing-Assessing" framework to systematically evaluate the spatial and mechanistic differences between these two metrics. We further investigate their pronounced non-stationary and threshold-based relationships with urban factors using a novel geographically weighted XGBoost (GW-XGBoost) and generalized additive model (GAM) workflow. Our results reveal substantial differences in the spatial patterns of LST and UTCI, along with marked spatial heterogeneity in how 2D and 3D urban factors impact these thermal metrics, as demonstrated by explainable GW-XGBoost models (test R2 = 0.855 for LST and 0.905 for UTCI). Crucially, spatially explicit SHAP shows that sky view factor plays a central role in explaining UTCI variability but exhibits a comparatively marginal independent contribution to LST, indicating that LST inadequately captures shading-driven and radiative processes governing actual human heat stress. Moreover, SHAP-GAM analysis indicates that higher albedo is associated with increased UTCI. These findings provide model-informed planning implications for integrating physiologically relevant thermal indices to support targeted heat risk management and human-centric urban planning.

cs.LG↗
arXiv2026

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then, two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks. Code is available at https://github.com/zwyang6/SaGe.

cs.CV↗
arXiv2026

Tracking Large-scale Shared Bikes with Inertial Motion Learning in GNSS Blocked Environments

Although Global Navigation Satellite Systems (GNSS) provide a general solution for bike tracking outdoors, there still exist complex riding environments where only inertial navigation systems work, such as urban canyons. Despite decades of research, localization using only low-cost inertial sensors still faces challenges such as cumulative drifts and poor robustness caused by filtering methods. Furthermore, sensors such as visual and LiDAR could provide reliable measurements, but they are not suitable for large-scale deployment. In this paper, we propose an inertial tracking framework that integrates bicycle mechanical constraints with a mixture-of-experts model. Specifically, we leverage multiple expert modules to capture shared representations and weight them through the gating mechanism, thus improving multi-task learning performance and enabling uncertainty-aware trajectory estimation. Furthermore, based on the mechanical transmission between the pedal and the rear wheel of a bike, we explore the intrinsic relationship between the rider's periodic pedalling behaviors and acceleration variations, and convert such patterns into bike's wheel speed for dynamic calibration. Experiments with real-world riding data from shared bikes of the DiDi ride-hailing platform demonstrate that our system improves the accuracy of baselines by at least 12%, with wheel speed errors below 0.5 m/s at 95-percentile.

cs.LG↗
arXiv2026

When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

A model can learn that the piano piece Für Elise is calm and reflective by listening to the audio or by reading a text description, but does it matter which route that knowledge took when it is later at risk of being forgotten? Forgetting research in multimodal models measures what knowledge is lost under adaptation, yet has not asked whether acquisition route affects how easily that knowledge is forgotten. We call this untested premise the Pathway-Invariant Assumption. Music understanding enables a clean test because a music clip and a canonical text description can be aligned to the same perceptual content, allowing the same knowledge unit to enter a model through listening or reading while the target remains fixed. Across multiple architecturally distinct audio-language models, we observe a consistent asymmetry: text-pathway knowledge is forgotten more than matched audio-pathway knowledge under identical adaptation pressure. To attribute this effect to route rather than confounds, we introduce the Paired Pathway Controlled Protocol (PPCP), a three-phase design that establishes matched pathway baselines, activates both pathways under symmetric supervision on the same knowledge pool, and applies identical forgetting pressure to both pathways. The gap is stable across models and gain-controlled analyses, persists when contradictory overwrite is replaced by correct-label cross-domain learning, remains under single-modality pressure, and is not removed by lightweight replay. Two independent routing-depth controls confirm that the effect is not explained by architectural depth, pointing to input representation as the dominant factor. Under PPCP, our results demonstrate that forgetting is highly route-dependent, establishing acquisition route as a new analytical dimension for forgetting research and multimodal system design.

cs.SD↗
arXiv2026

ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control

Reinforcement learning (RL) has shown promise in traffic signal control (TSC). However, its reliance on predefined states limits responsiveness to observable open-world events that are absent from training data. IoT-enabled intersections provide heterogeneous observations from roadside sensors and cameras, creating opportunities to improve RL adaptability to such events. To this end, we propose ReasonLight, a multimodal foundation model-enhanced RL framework for zero-shot TSC. ReasonLight integrates three sources of information: structured traffic measurements, multi-view camera observations, and candidate phase decisions from a pre-trained RL controller. Given an RL-proposed phase, ReasonLight extracts visual semantics from multi-view images and aligns them with compact sensor-derived scene descriptions. This alignment enables a semantic-guided refinement module to either preserve or adjust the proposed action according to traffic rules and event semantics. To ensure operational reliability, refined actions are constrained by the set of available phases. Any invalid decision is rejected, and the system falls back to the original RL action. We evaluate ReasonLight on two types of rare events not seen during RL training: emergency vehicle priority and temporary traffic regulation. Experimental results show that ReasonLight achieves zero-shot adaptation without retraining. It reduces emergency vehicle waiting time by up to 88.7% compared with the RL-only backbone while preserving comparable routine traffic performance.

cs.AI↗
arXiv2026

Physics-Aware Machine-Learning-Driven Inverse Design of Broadband Ultra-Open Acoustic Metamaterials

Ventilated acoustic silencers combing sound attenuation with high ventilation are pivotal for advanced noise control. However, balancing attenuation, bandwidth, openness, and thickness remains a high-dimensional challenge. Here, we report a physics-aware machine-learning-driven inverse design framework for ultra-open acoustic silencers (UAS). By leveraging Green's function-based parameterization, we physically decouple the design space into spectral and radial parameters, ensuring physical interpretability while reducing complexity. We introduce a two-stage forward prediction architecture that captures broadband envelopes and sharp resonant features via a coarse-to-fine strategy. Coupled with a population-based, hybrid-objective parallel (PHP) inverse strategy, our framework enables rapid exploration of non-convex landscapes, identifying hundreds of optimized candidates within seconds. Crucially, this framework uncovers hidden linear design rules that govern high-performance monolithic designs, acting as geometric proxies for optimal impedance-matching. We experimentally validate a family of prototypes: UAS-2 demonstrates the monolithic limit with high ventilation ratio, while UAS-3 demonstrates versatility in multi-mode interactions. To circumvent the trade-off ceiling of single-unit resonators, a parallel-composite architecture (UAS-4) is introduced to enhance performance through spatial interference distribution. Results confirm a broadband bandwidth exceeding 830 Hz achieved with an ultra-thin profile (0.1-0.2λ) and 80% ventilation. This work establishes a data-driven paradigm for discovering design principles in functional metamaterials.

physics.app-ph↗
arXiv2026

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to generate CAMs in WSSS. However, previous WSSS methods solely adopt CLIP's vision-language paired property for dense localization, neglecting its inherently limited dense knowledge across both visual and text modalities, which renders CAM generation suboptimal. In this work, we propose DiCLIP, a novel WSSS framework that leverages the generative diffusion model to enhance CLIP's dense knowledge across two modalities. Specifically, Visual Correlation Enhancement (VCE) and Text Semantic Augmentation (TSA) modules are proposed for dense prediction enhancement. To improve the spatial awareness of visual features, our VCE module utilizes diffusion's reliable spatial consistency to mitigate the over-smoothing issue in CLIP's attention. It designs the Attention Clustering Refinement (ACR) module to reliably extract diverse correlation maps from the diffusion model. The correlation maps act as a diversity bias for CLIP's self-attention, recursively pushing its visual features towards a more discriminative dense distribution. To augment the semantics of text embeddings, our TSA module argues that a single text modality is insufficient to encompass the variability of visual categories. Thus, we leverage diffusion's generative power to maintain a dynamic key-value cache model, shifting CAM generation from a patch-text matching mechanism to a novel visual knowledge retrieval paradigm. With these enhancements, DiCLIP not only outperforms state-of-the-art methods on PASCAL VOC and MS COCO but also significantly reduces training costs. Code is publicly available at https://github.com/zwyang6/DiCLIP.

cs.CV↗
arXiv2026

A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM

Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with breaking news. Recent advances in large language models (LLMs) enable leveraging externally retrieved reports as evidence for detection and explanation generation, but unverified reports may introduce inaccuracies. Moreover, effective explainable fake news detection should provide a comprehensible explanation for all aspects of a claim to assist the public in verifying its accuracy. To address these challenges, we propose a graph-enhanced defense framework (G-Defense) that provides fine-grained explanations based solely on unverified reports. Specifically, we construct a claim-centered graph by decomposing the news claim into several sub-claims and modeling their dependency relationships. For each sub-claim, we use the retrieval-augmented generation (RAG) technique to retrieve salient evidence and generate competing explanations. We then introduce a defense-like inference module based on the graph to assess the overall veracity. Finally, we prompt an LLM to generate an intuitive explanation graph. Experimental results demonstrate that G-Defense achieves state-of-the-art performance in both veracity detection and the quality of its explanations.

cs.CL↗
arXiv2026

Numerical reconstructions of a source term in a mobile-immobile diffusion model from the partial interior observation

We consider an inverse source problem in the two-time-scale mobile-immobile fractional diffusion model from partial interior observation. Theoretically, we combine the fractional Duhamel's principle with the weak vanishing property to establish the uniqueness of this inverse problem. Numerically, we adopt an optimal control approach for determining the source term. A coupled forward-backward system of equations is derived using the first-order optimality condition. Finally, we construct a finite element conjugate gradient algorithm for the numerical inversion of the source term. Several experiments are presented to show the utility of the method.

math.NA↗
arXiv2026

Identifying the source term in a viscoelastic membrane with a Riemann-Liouville time derivative by the partial interior observation

This paper studies an inverse source problem for a viscoelastic membrane, where the material's memory effect is characterized by the Riemann-Liouville fractional derivative. The problem is to recover the unknown source term from the limited interior observation data. We propose an optimal control framework to address this ill-posed inverse problem. The first-order optimality condition leads to a coupled system of forward and backward fractional partial differential equations. A numerical algorithm combining the finite element method and a conjugate gradient iterative scheme is then developed for the reconstruction of the source term. Several numerical examples are provided to demonstrate the effectiveness and robustness of the proposed method.

math.NA↗