Searcharxiv⌕ Search

arXiv subjects

Xiaoyang Wang

Publications and source records attributed to Xiaoyang Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools, limiting accessibility and reproducibility for the research community. In this work, we present \textbf{Cognitive Kernel-Pro}, a fully open-source and (to the maximum extent) free multi-module agent framework designed to democratize the development and evaluation of advanced AI agents. Within Cognitive Kernel-Pro, we systematically investigate the curation of high-quality training data for Agent Foundation Models, focusing on the construction of queries, trajectories, and verifiable answers across four key domains: web, file, code, and general reasoning. Furthermore, we explore novel strategies for agent test-time reflection and voting to enhance agent robustness and performance. We evaluate Cognitive Kernel-Pro on GAIA, achieving state-of-the-art results among open-source and free agents. Notably, our 8B-parameter open-source model surpasses previous leading systems such as WebDancer and WebSailor, establishing a new performance standard for accessible, high-capability AI agents. Code is available at https://github.com/Tencent/CognitiveKernel-Pro

cs.AI↗
arXiv2026

Crystal structure prediction with nuclear quantum and finite-temperature effects via deep free energy learning

Accurate crystal structure prediction (CSP) requires accounting for finite-temperature and nuclear quantum effects, yet first-principles evaluation of the free energy surface (FES) remains prohibitive for high-throughput searches. We observe that the self-consistent harmonic approximation (SCHA) FES, as a function of nuclear centroid positions, shares the same mathematical structure as a potential-energy surface and can therefore be directly learned by a deep neural network potential. The resulting deep free energy (DF) model, constructed via a two-level concurrent-learning workflow, evaluates free energies, forces, and stresses in a single forward pass. Applied to the La-Sc-H system at 200 GPa and 300 K, DF-based CSP reproduces the stability of the experimentally observed LaH10 and LaSc2H24, and discovers an unreported thermodynamically stable clathrate hydride: P4/mmm LaScH8. Benchmarked on the LaH10 system, the DF model achieves a 1.72*10^6-fold cost reduction relative to DFT-level SSCHA. The DF framework provides a scalable route for incorporating finite-temperature and nuclear quantum effects into high-throughput crystal structure prediction.

cond-mat.mtrl-sci↗
arXiv2026

A unified framework for efficient quantum simulation of nonlinear spectroscopy

Nonlinear spectroscopy is a cornerstone of quantum science, providing unique access to multi-point correlations, quantum coherence, and couplings that are invisible to linear methods. However, classical simulation of these phenomena is fundamentally limited by the exponential growth of the Hilbert space, and practical quantum algorithms for the nonlinear regime have remained largely unexplored. Here, we present a unified quantum algorithmic framework for computing $n$-th order nonlinear spectroscopies. By reformulating multi-time responses as a weighted sum of expectation values at finite pump amplitudes via a generalized parameter shift rule, our approach bypasses the costly evaluation of high-order commutators and time-dependent operator expansions. This reformulation enables efficient execution via real-time evolution on current quantum hardware, ensuring inherent noise resilience. We validate the framework on IBM's superconducting quantum processors, successfully obtain higher-order response functions of a 12-qubit XXZ spin-chain. Furthermore, the versatility of our method is demonstrated by resolving quasi-particle excitation spectra in spin-liquids and identifying interaction-induced cross-peaks in atomic systems. Our results establish a practical and scalable pathway for probing complex quantum dynamics on near-term quantum devices, extending the reach of quantum simulation into the nonlinear domain.

quant-ph↗
arXiv2026

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic connections that underlie their evolution. To disentangle these complex relationships, we introduce the concept of \textbf{data lineage} to the LLM ecosystem and propose an automated multi-agent framework to reconstruct the evolutionary graph of dataset development. Through large-scale lineage analysis, we characterize domain-specific structural patterns, such as vertical refinement in math-oriented datasets and horizontal aggregation in general-domain corpora. Moreover, we uncover pervasive systemic issues, including \textit{structural redundancy} induced by implicit dataset intersections and the \textit{propagation of benchmark contamination} along lineage paths. To demonstrate the practical value of lineage analysis for data construction, we leverage the reconstructed lineage graph to create a \textit{lineage-aware diversity-oriented dataset}. By anchoring instruction sampling at upstream root sources, this approach mitigates downstream homogenization and hidden redundancy, yielding a more diverse post-training corpus. We further highlight lineage-centric analysis as an efficient and robust topological alternative to sample-level dataset comparison for large-scale data ecosystems. By grounding data construction in explicit lineage structures, our work advances post-training data curation toward a more systematic and controllable paradigm.

cs.AI↗
arXiv2026

Varuna: Enabling Failure-Type Aware RDMA Failover

RDMA link failures can render connections temporarily unavailable, causing both performance degradation and significant recovery overhead. To tolerate such failures, production datacenters assign each primary link with a standby link and, upon failure, uniformly retransmit all in-flight RDMA request over the backup path. However, we observe that such blanket retransmission is unnecessary. In-flight requests can be split into pre-failure and post-failure categories depending on whether the responder has already executed. Retransmitting post-failure requests is not only redundant (consuming bandwidth), but also incorrect for non-idempotent operations, where duplicate execution can violate application semantics. We present Varuna, a failure-type-aware RDMA recovery mechanism that enables correct retransmission and us-level failover. Varuna piggybacks a lightweight completion log on every RDMA operation; after a link failure, this log deterministically reveals which in-flight requests were executed (post-failure) and which were lost (pre-failure). Varuna then retransmits only the pre-failure subset and fetches/recovers the return values for post-failure requests. Evaluated using synthetic microbenchmarks and end-to-end RDMA TPC-C transactions, Varuna incurs only 0.6-10% steady-state latency overhead in realistic applications, eliminates 65% of recovery retransmission time, preserves transactional consistency, and introduces zero connectivity rebuild overhead and negligible memory overhead during RDMA failover.

cs.DC↗
arXiv2026

Phase transitions in parametrized quantum circuits

Phase transitions are among the most intriguing phenomena in physical systems, yet their behavior near criticality remain challenging to study using classical algorithms. Parameterized quantum circuits (PQCs) offer a promising approach to investigating such regimes on practical quantum computers. However, in order to use it to probe critical behavior, a PQC itself should be non-trivial and exhibit a phase transition and non-analyticity -- a property that has not yet been clearly identified. In this work, we identify a mechanism for generating non-analyticities intrinsically in PQCs. As a concrete realization, we construct a class of sequential PQCs whose observable expectation value is a non-analytic function of the circuit parameter in the infinite volume limit, showing that the prepared PQC states undergo a phase transition at the non-analytic points. The entanglement and the identified order parameter have distinct behaviors in different phases, revealing a phase diagram of the PQC state. We show that classical simulation of this PQC based on tensor networks and Pauli propagation gets less efficient in the vicinity of the phase transition point, indicating a physically motivated route towards practical quantum advantage using PQCs with phase transitions.

quant-ph↗
arXiv2026

Quantum Simulations of Opinion Dynamics

Consensus formation is a central problem in collective behavior. In this work, we develop quantum models of opinion dynamics that can be exactly solved and implemented on current quantum hardware. By exploiting quantum superposition, measurement-induced state collapse, and entanglement, our framework captures key features of opinion evolution and allows a systematic investigation of how network connectivity shapes consensus formation. We demonstrate our approach using practical quantum circuits and validate representative cases on IBM Quantum devices for the open-chain. These findings pave the way for further exploration into quantum-enhanced social modeling, highlighting the potential of near-term quantum computers for simulating collective behavior in complex systems.

physics.soc-ph↗
arXiv2026

C$^{2}$TC: A Training-Free Framework for Efficient Tabular Data Condensation

Tabular data is the primary data format in industrial relational databases, underpinning modern data analytics and decision-making. However, the increasing scale of tabular data poses significant computational and storage challenges to learning-based analytical systems. This highlights the need for data-efficient learning, which enables effective model training and generalization using substantially fewer samples. Dataset condensation (DC) has emerged as a promising data-centric paradigm that synthesizes small yet informative datasets to preserve data utility while reducing storage and training costs. However, existing DC methods are computationally intensive due to reliance on complex gradient-based optimization. Moreover, they often overlook key characteristics of tabular data, such as heterogeneous features and class imbalance. To address these limitations, we introduce C$^{2}$TC (Class-Adaptive Clustering for Tabular Condensation), the first training-free tabular dataset condensation framework that jointly optimizes class allocation and feature representation, enabling efficient and scalable condensation. Specifically, we reformulate the dataset condensation objective into a novel class-adaptive cluster allocation problem (CCAP), which eliminates costly training and integrates adaptive label allocation to handle class imbalance. To solve the NP-hard CCAP, we develop HFILS, a heuristic local search that alternates between soft allocation and class-wise clustering to efficiently obtain high-quality solutions. Moreover, a hybrid categorical feature encoding (HCFE) is proposed for semantics-preserving clustering of heterogeneous discrete attributes. Extensive experiments on 10 real-world datasets demonstrate that C$^{2}$TC improves efficiency by at least 2 orders of magnitude over state-of-the-art baselines, while achieving superior downstream performance.

cs.LG↗
arXiv2026

General transformation neural networks: A class of parametrized functions for high-dimensional function approximation

We propose a novel class of neural network-like parametrized functions, i.e., general transformation neural networks (GTNNs), for high-dimensional approximation. Conventional deep neural networks sometimes perform less accurately on learning problems trained with gradient descent, especially when the target function is oscillatory. To improve accuracy, we generalize the neuron's affine transformation to a broader class of functions that can capture complex shapes and offer greater capacity. Specifically, we discuss three types of GTNNs in detail: the cubic, quadratic and trigonometric transformation neural networks (CTNNs, QTNNs and TTNNs). We perform an approximation error analysis of GTNNs, presenting their universal approximation properties for continuous functions, error bounds for Barron-type functions and error bounds of deep architectures. Several numerical examples of regression problems are presented, demonstrating that CTNNs/QTNNs/TTNNs achieve higher accuracy than conventional fully connected neural networks.

math.NA↗
arXiv2026

MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning

Large Language Models (LLMs) have achieved impressive reasoning abilities, but struggle with temporal understanding, especially when questions involve multiple entities, compound operators, and evolving event sequences. Temporal Knowledge Graphs (TKGs), which capture vast amounts of temporal facts in a structured format, offer a reliable source for temporal reasoning. However, existing TKG-based LLM reasoning methods still struggle with four major challenges: maintaining temporal faithfulness in multi-hop reasoning, achieving multi-entity temporal synchronization, adapting retrieval to diverse temporal operators, and reusing prior reasoning experience for stability and efficiency. To address these issues, we propose MemoTime, a memory-augmented temporal knowledge graph framework that enhances LLM reasoning through structured grounding, recursive reasoning, and continual experience learning. MemoTime decomposes complex temporal questions into a hierarchical Tree of Time, enabling operator-aware reasoning that enforces monotonic timestamps and co-constrains multiple entities under unified temporal bounds. A dynamic evidence retrieval layer adaptively selects operator-specific retrieval strategies, while a self-evolving experience memory stores verified reasoning traces, toolkit decisions, and sub-question embeddings for cross-type reuse. Comprehensive experiments on multiple temporal QA benchmarks show that MemoTime achieves overall state-of-the-art results, outperforming the strong baseline by up to 24.0%. Furthermore, MemoTime enables smaller models (e.g., Qwen3-4B) to achieve reasoning performance comparable to that of GPT-4-Turbo.

cs.CL↗
arXiv2026

Beyond Homophily: Community Search on Heterophilic Graphs

Community search aims to identify a refined set of nodes that are most relevant to a given query, supporting tasks ranging from fraud detection to recommendation. Unlike homophilic graphs, many real-world networks are heterophilic, where edges predominantly connect dissimilar nodes. Therefore, structural signals that once reflected smooth, low-frequency similarity now appear as sharp, high-frequency contrasts. However, both classical algorithms (e.g., k-core, k-truss) and recent ML-based models struggle to achieve effective community search on heterophilic graphs, where edge signs or semantics are generally unknown. Algorithm-based methods often return communities with mixed class labels, while GNNs, built on homophily, smooth away meaningful signals and blur community boundaries. Therefore, we propose Adaptive Community Search (AdaptCS), a lightweight framework featuring three key designs: (i) an AdaptCS Encoder that disentangles multi-hop and multi-frequency signals, enabling the model to capture both smooth (homophilic) and contrastive (heterophilic) relations; (ii) a memory-efficient low-rank optimization that removes the main computational bottleneck and ensures model scalability; and (iii) an Adaptive Community Score (ACS) that guides online search by balancing embedding similarity and topological relations. Extensive experiments on both heterophilic and homophilic benchmarks demonstrate that AdaptCS outperforms the best-performing baseline by an average of 11% in F1-score, retains robustness across heterophily levels, and achieves up to 2 orders of magnitude speedup over the strongest ML-based CS baselines.

cs.SI↗
arXiv2026

CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use

AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to such settings remains difficult: realistic objectives often lack verifiable rewards and instead emphasize open-ended behaviors; moreover, RL for multi-turn, multi-step agentic tool use is still underexplored; and building and maintaining executable tool environments is costly, limiting scale and coverage. We propose CM2, an RL framework that replaces verifiable outcome rewards with checklist rewards. CM2 decomposes each turn's intended behavior into fine-grained binary criteria with explicit evidence grounding and structured metadata, turning open-ended judging into more stable classification-style decisions. To balance stability and informativeness, our method adopts a strategy of sparse reward assignment but dense evaluation criteria. Training is performed in a scalable LLM-simulated tool environment, avoiding heavy engineering for large tool sets. Experiments show that CM2 consistently improves over supervised fine-tuning. Starting from an 8B Base model and training on an 8k-example RL dataset, CM2 improves over the SFT counterpart by 8 points on tau^-Bench, by 10 points on BFCL-V4, and by 12 points on ToolSandbox. The results match or even outperform similarly sized open-source baselines, including the judging model. CM2 thus provides a scalable recipe for optimizing multi-turn, multi-step tool-using agents without relying on verifiable rewards. Code provided by the open-source community: https://github.com/namezhenzhang/CM2-RLCR-Tool-Agent.

cs.AI↗
arXiv2026

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation

Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, we propose PRoH, a dynamic Planning and Reasoning over Knowledge Hypergraphs framework. PRoH incorporates three core innovations: (i) a context-aware planning module that sketches the local KH neighborhood to guide structurally grounded reasoning plan generation; (ii) a structured question decomposition process that organizes subquestions as a dynamically evolving Directed Acyclic Graph (DAG) to enable adaptive, multi-trajectory exploration; and (iii) an Entity-Weighted Overlap (EWO)-guided reasoning path retrieval algorithm that prioritizes semantically coherent hyperedge traversals. Experiments across multiple domains demonstrate that PRoH achieves state-of-the-art performance, surpassing the prior SOTA model HyperGraphRAG by an average of 19.73% in F1 and 8.41% in Generation Evaluation (G-E) score, while maintaining strong robustness in long-range multi-hop reasoning tasks.

cs.CL↗
arXiv2026

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. Starting from a single base LLM, R-Zero initializes two independent models with distinct roles, a Challenger and a Solver. These models are optimized separately and co-evolve through interaction: the Challenger is rewarded for proposing tasks near the edge of the Solver capability, and the Solver is rewarded for solving increasingly challenging tasks posed by the Challenger. This process yields a targeted, self-improving curriculum without any pre-existing tasks and labels. Empirically, R-Zero substantially improves reasoning capability across different backbone LLMs, e.g., boosting the Qwen3-4B-Base by +6.49 on math-reasoning benchmarks and +7.54 on general-domain reasoning benchmarks.

cs.LG↗
arXiv2026

Exploring Noisy Quantum Thermodynamical Processes via the Depolarizing-Channel Approximation

Noise and errors are unavoidable in any realistic quantum process, including processes designed to reduce noise and errors in the first place. In particular, quantum thermodynamical protocols for cooling can be significantly affected, potentially altering both their performance and efficiency. Analytically characterizing the impact of such errors becomes increasingly challenging as the system size grows, particularly in deep quantum circuits where noise can accumulate in complex ways. To address this, we introduce a general framework for approximating the cumulative effect of gate-dependent noise using a global depolarizing channel. We specify the regime in which this approximation provides a reliable description of the noisy dynamics. Applying our framework to the thermodynamical two-sort algorithmic cooling (TSAC) protocol, we analytically derive its asymptotic cooling limit in the presence of noise. Using the cooling limit, the optimal cooling performance is achieved by a finite number of qubits--distinguished from the conventional noiseless TSAC protocol by an infinite number of qubits--and fundamental bounds on the achievable ground-state population are derived. This approach opens new avenues for exploring noisy quantum thermodynamical processes.

quant-ph↗
arXiv2026

PrivGemo: Privacy-Preserving Dual-Tower Graph Retrieval for Empowering LLM Reasoning with Memory Augmentation

Knowledge graphs (KGs) provide structured evidence that can ground large language model (LLM) reasoning for knowledge-intensive question answering. However, many practical KGs are private, and sending retrieved triples or exploration traces to closed-source LLM APIs introduces leakage risk. Existing privacy treatments focus on masking entity names, but they still face four limitations: structural leakage under semantic masking, uncontrollable remote interaction, fragile multi-hop and multi-entity reasoning, and limited experience reuse for stability and efficiency. To address these issues, we propose PrivGemo, a privacy-preserving retrieval-augmented framework for KG-grounded reasoning with memory-guided exposure control. PrivGemo uses a dual-tower design to keep raw KG knowledge local while enabling remote reasoning over an anonymized view that goes beyond name masking to limit both semantic and structural exposure. PrivGemo supports multi-hop, multi-entity reasoning by retrieving anonymized long-hop paths that connect all topic entities, while keeping grounding and verification on the local KG. A hierarchical controller and a privacy-aware experience memory further reduce unnecessary exploration and remote interactions. Comprehensive experiments on six benchmarks show that PrivGemo achieves overall state-of-the-art results, outperforming the strongest baseline by up to 17.1%. Furthermore, PrivGemo enables smaller models (e.g., Qwen3-4B) to achieve reasoning performance comparable to that of GPT-4-Turbo.

cs.CL↗
arXiv2026

A Versatile Multimodal Agent for Multimedia Content Generation

With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.

cs.CV↗
arXiv2025

Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets

The construction of Supervised Fine-Tuning (SFT) datasets is a critical yet under-theorized stage in the post-training of Large Language Models (LLMs), as prevalent practices often rely on heuristic aggregation without a systematic understanding of how individual samples contribute to model performance. In this report, we propose a paradigm shift from ad-hoc curation to a closed-loop dataset engineering framework using OpenDataArena (ODA), which leverages value-anchored rankings and multi-dimensional analysis to transform value benchmarking into feedback signals guiding dataset construction. We instantiate this methodology through two new datasets: \textbf{ODA-Math-460k}, a specialized mathematics reasoning dataset that utilizes a novel two-stage difficulty-aware pipeline to achieve State-of-the-Art (SOTA) results on benchmarks such as AIME and HMMT, and \textbf{ODA-Mixture (100k \& 500k)}, a series of multi-domain instruction datasets built via an ``Anchor-and-Patch'' strategy that outperforms significantly larger open-source baselines. Our empirical results demonstrate that ODA-driven datasets significantly improve both domain-specific reasoning and general utility while achieving superior data efficiency, validating a transition toward data-centric AI where transparent evaluation serves as the primary engine for engineering high-quality training data.

cs.CL↗