arXiv subjects

Chengyu Wang

Publications and source records attributed to Chengyu Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use

Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typically performed under strict cost and latency constraints, making small agentic models highly desirable. In this paper, we introduce the AgenticQwen family of models, trained via multi-round reinforcement learning (RL) on synthetic data and a limited amount of open-source data. Our training framework combines reasoning RL and agentic RL with dual data flywheels that automatically generate increasingly challenging tasks. The reasoning flywheel increases task difficulty by learning from errors, while the agentic flywheel expands linear workflows into multi-branch behavior trees that better reflect the decision complexity of real-world applications. We validate AgenticQwen on public benchmarks and in an industrial agent system. The models achieve strong performance on multiple agentic benchmarks, and in our industrial agent system, close the gap with much larger models on search and data analysis tasks. Model checkpoints and part of the synthetic data: https://huggingface.co/collections/alibaba-pai/agenticqwen. Data synthesis and RL training code: https://github.com/haruhi-sudo/data_synth_and_rl. The data synthesis pipeline is also integrated into EasyDistill: https://github.com/modelscope/easydistill.

cs.CL↗

arXiv2026

Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes. We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments. Specifically, a strong teacher model creates novel tasks and tool ecosystems, then rewrites them into intentionally underspecified instructions. This compels agents to actively query users for missing details. When handling synthetic tasks, an LLM-based user simulator provides user-private information, while a mock tool system delivers stable tool responses. For rewards, task-level rubrics are constructed based on required subgoals, user-agent interactions, and forbidden behaviors. Across 14 challenging datasets in math, search, and tool use, models trained on our synthetic data achieve substantial gains, with small models outperforming larger baselines.

cs.CL↗

arXiv2026

VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on complex additional training or external models for compression, which limits scalability and discards critical fine-grained information. In this paper, we propose VTC-R1, a new efficient reasoning paradigm that integrates vision-text compression into the reasoning process. Instead of processing lengthy textual traces, VTC-R1 renders intermediate reasoning segments into compact images, which are iteratively fed back into vision-language models as "optical memory." We construct a training dataset based on OpenR1-Math-220K achieving 3.4x token compression and fine-tune representative VLMs-Glyph and Qwen3-VL. Extensive experiments on benchmarks such as MATH500, AIME25, AMC23 and GPQA-D demonstrate that VTC-R1 consistently outperforms standard long-context reasoning. Furthermore, our approach significantly improves inference efficiency, achieving 2.7x speedup in end-to-end latency, highlighting its potential as a scalable solution for reasoning-intensive applications. Our code is available at https://github.com/w-yibo/VTC-R1.

cs.CL↗

arXiv2025

MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images

We present MatDecompSDF, a novel framework for recovering high-fidelity 3D shapes and decomposing their physically-based material properties from multi-view images. The core challenge of inverse rendering lies in the ill-posed disentanglement of geometry, materials, and illumination from 2D observations. Our method addresses this by jointly optimizing three neural components: a neural Signed Distance Function (SDF) to represent complex geometry, a spatially-varying neural field for predicting PBR material parameters (albedo, roughness, metallic), and an MLP-based model for capturing unknown environmental lighting. The key to our approach is a physically-based differentiable rendering layer that connects these 3D properties to the input images, allowing for end-to-end optimization. We introduce a set of carefully designed physical priors and geometric regularizations, including a material smoothness loss and an Eikonal loss, to effectively constrain the problem and achieve robust decomposition. Extensive experiments on both synthetic and real-world datasets (e.g., DTU) demonstrate that MatDecompSDF surpasses state-of-the-art methods in geometric accuracy, material fidelity, and novel view synthesis. Crucially, our method produces editable and relightable assets that can be seamlessly integrated into standard graphics pipelines, validating its practical utility for digital content creation.

cs.CV↗

arXiv2025

Video Event Reasoning and Prediction by Fusing World Knowledge from LLMs with Vision Foundation Models

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To bridge this cognitive gap, we propose a novel framework that synergistically fuses a powerful Vision Foundation Model (VFM) for deep visual perception with a Large Language Model (LLM) serving as a knowledge-driven reasoning core. Our key technical innovation is a sophisticated fusion module, inspired by the Q-Former architecture, which distills complex spatiotemporal and object-centric visual features into a concise, language-aligned representation. This enables the LLM to effectively ground its inferential processes in direct visual evidence. The model is trained via a two-stage strategy, beginning with large-scale alignment pre-training on video-text data, followed by targeted instruction fine-tuning on a curated dataset designed to elicit advanced reasoning and prediction skills. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple challenging benchmarks. Notably, it exhibits remarkable zero-shot generalization to unseen reasoning tasks, and our in-depth ablation studies validate the critical contribution of each architectural component. This work pushes the boundary of machine perception from simple recognition towards genuine cognitive understanding, paving the way for more intelligent and capable AI systems in robotics, human-computer interaction, and beyond.

cs.CV↗

arXiv2025

Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Models

The integration of Large Language Models (LLMs) into robotics has unlocked unprecedented capabilities in high-level task planning. However, most current systems operate in an open-loop fashion, where LLMs act as one-shot planners, rendering them brittle and unable to adapt to unforeseen circumstances in dynamic physical environments. To overcome this limitation, this paper introduces the "Think, Act, Learn" (T-A-L) framework, a novel architecture that enables an embodied agent to autonomously learn and refine its policies through continuous interaction. Our framework establishes a closed-loop cycle where an LLM first "thinks" by decomposing high-level commands into actionable plans. The robot then "acts" by executing these plans while gathering rich, multimodal sensory feedback. Critically, the "learn" module processes this feedback to facilitate LLM-driven self-reflection, allowing the agent to perform causal analysis on its failures and generate corrective strategies. These insights are stored in an experiential memory to guide future planning cycles. We demonstrate through extensive experiments in both simulation and the real world that our T-A-L agent significantly outperforms baseline methods, including open-loop LLMs, Behavioral Cloning, and traditional Reinforcement Learning. Our framework achieves over a 97% success rate on complex, long-horizon tasks, converges to a stable policy in an average of just 9 trials, and exhibits remarkable generalization to unseen tasks. This work presents a significant step towards developing more robust, adaptive, and truly autonomous robotic agents.

cs.RO↗

arXiv2025

Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning

Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a novel framework designed to embed an explicit model of causal physics within an LLM. Our approach incorporates a dedicated Causal Physics Module (CPM) and a new training objective called Causal Intervention Loss, encouraging the model to learn cause-and-effect relationships from multimodal data. By training the model to predict the outcomes of hypothetical interventions instead of merely capturing statistical correlations, CWMI develops a robust internal representation of physical laws. Experimental results show that CWMI significantly outperforms state-of-the-art LLMs on zero-shot physical reasoning tasks, including the PIQA benchmark and our newly proposed PhysiCa-Bench dataset. These findings demonstrate that inducing a causal world model is a critical step toward more reliable and generalizable AI systems.

cs.LG↗

arXiv2025

An Information-Theoretic Framework for Robust Large Language Model Editing

Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their accuracy and restrict their safe deployment. Developing efficient strategies for updating model knowledge without the expense and disruption of full retraining remains a critical challenge. Current model editing techniques frequently struggle to generalize corrections beyond narrow domains, leading to unintended consequences and limiting their practical impact. Here, we introduce a novel framework for editing LLMs, grounded in information bottleneck theory. This approach precisely compresses and isolates the essential information required for generalizable knowledge correction while minimizing disruption to unrelated model behaviors. Building upon this foundation, we present the Information Bottleneck Knowledge Editor (IBKE), which leverages compact latent representations to guide gradient-based updates, enabling robust and broadly applicable model editing. We validate IBKE's effectiveness across multiple LLM architectures and standard benchmark tasks, demonstrating state-of-the-art accuracy and improved generality and specificity of edits. These findings establish a theoretically principled and practical paradigm for open-domain knowledge editing, advancing the utility and trustworthiness of LLMs in real-world applications.

cs.CL↗

arXiv2025

Observation of a Stripe/nematic Phase of Composite Fermions

Electronic stripe/nematic phases are fascinating strongly-correlated states characterized by spontaneous rotational symmetry breaking. In the quantum Hall regime, such phases typically emerge at half-filled, high-orbital-index ($N\geq2$) Landau levels (LLs) where the short-range Coulomb interaction is softened by the nodes of electron wave functions. In the lowest ($N=0$) LLs, these phases are not expected. Instead, composite fermion (CF) liquids and fractional quantum Hall states, which are well explained in the picture of weakly interacting CF quasiparticles, are favored. Here we report the observation of an unexpected stripe/nematic phase in the \textit{lowest} LL at filling factor $ν=5/8$ in ultrahigh-quality GaAs two-dimensional \textit{hole} systems, evinced by a pronounced in-plane transport anisotropy. Remarkably, $ν=5/8$ can be mapped to a half-filled, high-index CF LL ($N_{\text{CF}}=2$), analogous to the $N=2$ hole LL. Our finding signals a novel stripe/nematic phase of CFs, driven by the residual long-range interaction among these emergent quasiparticles. This phase is surprisingly robust, surviving up to $\sim$100 mK. Its absence in electron-type systems suggests that severe LL mixing stemming from the large hole effective mass and non-linear LL fan diagram plays a crucial role in modifying the CF-CF interaction.

cond-mat.mes-hall↗

arXiv2025

MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image

Multimodal large language models (MLLMs) have shown remarkable progress in high-level semantic tasks such as visual question answering, image captioning, and emotion recognition. However, despite advancements, there remains a lack of standardized benchmarks for evaluating MLLMs performance in multi-object sentiment analysis, a key task in semantic understanding. To address this gap, we introduce MOSABench, a novel evaluation dataset designed specifically for multi-object sentiment analysis. MOSABench includes approximately 1,000 images with multiple objects, requiring MLLMs to independently assess the sentiment of each object, thereby reflecting real-world complexities. Key innovations in MOSABench include distance-based target annotation, post-processing for evaluation to standardize outputs, and an improved scoring mechanism. Our experiments reveal notable limitations in current MLLMs: while some models, like mPLUG-owl and Qwen-VL2, demonstrate effective attention to sentiment-relevant features, others exhibit scattered focus and performance declines, especially as the spatial distance between objects increases. This research underscores the need for MLLMs to enhance accuracy in complex, multi-object sentiment analysis tasks and establishes MOSABench as a foundational tool for advancing sentiment analysis capabilities in MLLMs.

cs.CV↗

arXiv2025

UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models

Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited range of editing evaluation. They often overlook the broad scope of editing demands and the diversity of ripple effects resulting from edits. In this context, we introduce UniEdit, a unified benchmark for LLM editing grounded in open-domain knowledge. First, we construct editing samples by selecting entities from 25 common domains across five major categories, utilizing the extensive triple knowledge available in open-domain knowledge graphs to ensure comprehensive coverage of the knowledge domains. To address the issues of generality and locality in editing, we design an Neighborhood Multi-hop Chain Sampling (NMCS) algorithm to sample subgraphs based on a given knowledge piece to entail comprehensive ripple effects to evaluate. Finally, we employ proprietary LLMs to convert the sampled knowledge subgraphs into natural language text, guaranteeing grammatical accuracy and syntactical diversity. Extensive statistical analysis confirms the scale, comprehensiveness, and diversity of our UniEdit benchmark. We conduct comprehensive experiments across multiple LLMs and editors, analyzing their performance to highlight strengths and weaknesses in editing across open knowledge domains and various evaluation criteria, thereby offering valuable insights for future research endeavors.

cs.CL↗

arXiv2025

Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment

The reasoning capabilities of large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, have seen substantial advancements through deep thinking. However, these enhancements come with significant resource demands, underscoring the need for training effective small reasoning models. A critical challenge is that small models possess different reasoning capacities and cognitive trajectories compared with their larger counterparts. Hence, directly distilling chain-of-thought (CoT) rationales from large LRMs to smaller ones can sometimes be ineffective and often requires a substantial amount of annotated data. In this paper, we first introduce a novel Critique-Rethink-Verify (CRV) system, designed for training smaller yet powerful LRMs. Our CRV system consists of multiple LLM agents, each specializing in unique tasks: (i) critiquing the CoT rationales according to the cognitive capabilities of smaller models, (ii) rethinking and refining these CoTs based on the critiques, and (iii) verifying the correctness of the refined results. Building on the CRV system, we further propose the Cognitive Preference Optimization (CogPO) algorithm to continuously enhance the reasoning abilities of smaller models by aligning their reasoning processes with their cognitive capacities. Comprehensive evaluations on challenging reasoning benchmarks demonstrate the efficacy of our CRV+CogPO framework, which outperforms other methods by a large margin.

cs.CL↗

arXiv2025

Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series

Recently, the demand for small and efficient reasoning models to support real-world applications has driven the development of knowledge distillation techniques that balance reasoning performance and inference speed. In this paper, we further extend the DistilQwen model family, initialized from the Qwen models, by introducing four model series specifically designed to meet industrial requirements. The distilled model collection comprises: (1) slow-thinking models, optimized for reasoning tasks that require high accuracy; (2) two series of adaptive-thinking models, which dynamically adjust reasoning strategies based on input tasks to maximize efficiency across diverse scenarios; and (3) distilled reward models, which enable further reinforcement learning of reasoning models using distilled knowledge. Comprehensive evaluations across multiple benchmarks demonstrate both high inference efficiency and strong reasoning performance for these models, as well as the practical utility of distilled reward models. We further show that these models support industry practitioners by providing scalable training and inference functionalities on the Alibaba Cloud PAI (Platform for Artificial Intelligence) platform.

cs.CL↗

arXiv2025

Fractional quantum Hall state at $ν= 1/2$ with energy gap up to 6 K, and possible transition from one- to two-component state

The fractional quantum Hall state (FQHS) observed in the lowest Landau level at filling factor $ν=1/2$ in wide quantum wells has been enigmatic for decades because the two-dimensional electron system (2DES) has a bilayer charge distribution but with significant interlayer tunneling. Of particular interest is whether the 1/2 FQHS in this system has a one-component (1C) or two-component (2C) origin; these are typically identified as the Pfaffian (non-Abelian) or the $Ψ_{331}$ (Abelian) FQHSs, respectively. We report here our experimental study of the evolution of the correlated states of an ultrahigh-quality 2DES confined to a 72.5-nm-wide GaAs quantum well. At the lowest densities, the 2DES displays only odd-denominator FQHSs, and the ground state at $ν= 1/2$ is a composite fermion Fermi sea. As the density is increased, a FQHS emerges at $ν= 1/2$, and becomes very strong. In a finite density range where the 1/2 FQHS is strongest, we also observe its daughter FQHSs at $ν= 8/17$ and 7/13, consistent with the theoretically expected daughter states of a Pfaffian 1/2 FQHS. At the highest densities, the 2DES becomes 2C, signaled by the emergence of a bilayer Wigner crystal state and the transitions of FQHSs flanking $ν=1/2$. The 1/2 FQHS remains robust near this transition and, notably, its charge transport energy gap exhibits an \textit{upward} cusp with a maximum value of about 6 K on the 1C side of the transition; this is the largest gap reported for any even-denominator FQHS. Our observation of the transition of the 2DES ground states near $ν=1/2$ to 2C states at high densities, and our measurements of the robustness of the 1/2 FQHS against charge distribution asymmetry, suggest that the 1/2 FQHS also makes a transition from 1C to 2C. Such a transition from a non-Abelian to Abelian state can open avenues for topological quantum information and quantum criticality.

cond-mat.mes-hall↗

arXiv2025

Even-denominator fractional quantum Hall states with spontaneously broken rotational symmetry

The interplay between the fractional quantum Hall effect and nematicity is intriguing as it links emerging topological order and spontaneous symmetry breaking. Anisotropic fractional quantum Hall states (FQHSs) have indeed been reported in GaAs quantum wells but only in tilted magnetic fields, where the in-plane field explicitly breaks the rotational symmetry. Here we report the observation of FQHSs with highly anisotropic longitudinal resistances in purely perpendicular magnetic fields at even-denominator Landau level (LL) fillings ν = 5/2 and 7/2 in ultrahigh-quality GaAs two-dimensional hole systems. The coexistence of FQHSs and spontaneous symmetry breaking at half fillings signals the emergence of nematic FQHSs which also likely harbor non-Abelian quasiparticle excitations. By gate tuning the hole density, we observe a phase transition from an anisotropic, developing FQHS to an isotropic composite fermion Fermi sea at ν = 7/2. Our calculations suggest that the mixed orbital components in the partially occupied LL play a key role in the competition and interplay between topological and nematic orders.

cond-mat.mes-hall↗

arXiv2025

Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision

The majority of AI models in imaging and vision are customized to perform on specific high-precision task. However, this strategy is inefficient for applications with a series of modular tasks, since each requires a mapping into a disparate latent domain. To address this inefficiency, we proposed a universal Neural Space (NS), where an encoder-decoder framework pre-computes features across vision and imaging tasks. Our encoder learns transformation aware, generalizable representations, which enable multiple downstream AI modules to share the same feature space. This architecture reduces redundancy, improves generalization across domain shift, and establishes a foundation for effecient multi-task vision pipelines. Furthermore, as opposed to larger transformer backbones, our backbone is lightweight and CNN-based, allowing for wider across hardware. We furthur demonstrate that imaging and vision modules, such as demosaicing, denoising, depth estimation and semantic segmentation can be performed efficiently in the NS.

cs.CV↗

arXiv2025

Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis

In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion representation remains a significant challenge for these T2V models. Existing approaches often adapt pre-trained text-to-image (T2I) models to refine video frames, leading to issues such as flickering and artifacts due to inconsistencies across frames. In this paper, we introduce EVS, a training-free Encapsulated Video Synthesizer that composes T2I and T2V models to enhance both visual fidelity and motion smoothness of generated videos. Our approach utilizes a well-trained diffusion-based T2I model to refine low-quality video frames by treating them as out-of-distribution samples, effectively optimizing them with noising and denoising steps. Meanwhile, we employ T2V backbones to ensure consistent motion dynamics. By encapsulating the T2V temporal-only prior into the T2I generation process, EVS successfully leverages the strengths of both types of models, resulting in videos of improved imaging and motion quality. Experimental results validate the effectiveness of our approach compared to previous approaches. Our composition process also leads to a significant improvement of 1.6x-4.5x speedup in inference time. Source codes: https://github.com/Tonniia/EVS.

cs.CV↗

arXiv2025

EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models

In this paper, we present EasyDistill, a comprehensive toolkit designed for effective black-box and white-box knowledge distillation (KD) of large language models (LLMs). Our framework offers versatile functionalities, including data synthesis, supervised fine-tuning, ranking optimization, and reinforcement learning techniques specifically tailored for KD scenarios. The toolkit accommodates KD functionalities for both System 1 (fast, intuitive) and System 2 (slow, analytical) models. With its modular design and user-friendly interface, EasyDistill empowers researchers and industry practitioners to seamlessly experiment with and implement state-of-the-art KD strategies for LLMs. In addition, EasyDistill provides a series of robust distilled models and KD-based industrial solutions developed by us, along with the corresponding open-sourced datasets, catering to a variety of use cases. Furthermore, we describe the seamless integration of EasyDistill into Alibaba Cloud's Platform for AI (PAI). Overall, the EasyDistill toolkit makes advanced KD techniques for LLMs more accessible and impactful within the NLP community.

cs.CL↗