arXiv subjects

Rui Wang

Publications and source records attributed to Rui Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Skill-based Agentic Evaluation for Real-time Data Science Tasks

We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid scoring. Consider this example query: "what were last week's audience sizes"---the reference answer changes as the underlying data changes, so static references become outdated and standard LLM-as-a-judge pipelines cannot verify responses against a fixed ground truth. Our central contribution, ground-truth-as-code, encodes each expected answer as an executable reference function that recomputes the answer directly from live data at evaluation time, ensuring the reference remains consistent with the system it describes. We combine this with a factoid-level, format-agnostic judge that decomposes both the agent's response and the computed ground truth into atomic claims and scores precision, recall, and accuracy over them, irrespective of the response format (prose, list, table, HTML, etc.). The approach is applicable to agents whose expected outputs can be expressed as executable data computations. We validate the framework through a human--LLM agreement study on an internally developed machine learning skill deployed in production, using a synthetic database constructed to reproduce production schemas and entity relationships. Relative to a natural-language ground-truth baseline, our method achieves a 29% improvement in the Matthews Correlation Coefficient (MCC)---a class-balanced measure of agreement between expert annotators and LLM-as-a-judge predictions---and a 16% reduction in token consumption per test case, while a self-directed baseline lacking explicit ground truth is anti-correlated with human judgment. Agents that perform multi-source data integration and computation over non-stationary data are routinely deployed in industry; we propose ground-truth-as-code as a practical methodology for their evaluation.

cs.AI↗

arXiv2026

One- and two-dimensional cluster states for topological phase simulation and measurement-based quantum computation

Quantum entanglement is a fundamental resource for quantum information processing and serves as a critical benchmark for quantum hardware performance. Cluster states are a special class of entangled states that serve as universal resources for measurement-based quantum computation and possess an intrinsic symmetry-protected topological order, which confers robustness against symmetry-respecting noise. Here we report the scalable preparation and verification of genuine multipartite cluster states on the 105-qubit Zuchongzhi 3.1 superconducting processor. We achieve one-dimensional cluster states of up to 95 qubits and two-dimensional cluster states of up to 72 qubits. The symmetry-protected topological cluster states exhibit input-state-dependent robustness under symmetry-breaking perturbations due to an operational parity structure that enhances the performance of measurement-based quantum computation. Furthermore, we use our two-dimensional cluster states to implement the Deutsch-Jozsa algorithm within the measurement-based quantum computation framework, achieving higher output-state fidelity compared with traditional circuit-based models and a query efficiency advantage over classical approaches. Our work establishes a scalable platform that combines large-scale entanglement generation, symmetry-protected topological order and practical quantum algorithms to enable robust, fault-tolerant measurement-based quantum computation.

quant-ph↗

arXiv2026

EchoFuzz: Empowering Smart Contract Fuzzing with Large Language Models

Smart contracts, serving as the cornerstone of decentralized applications, autonomously manage trillion-dollar digital assets, making them attractive targets for attacks. Fuzzing has emerged as a promising technique for detecting vulnerabilities in smart contracts, yet existing methods face two main challenges. (1) The logical gap in state transitions and combinatorial redundancy hinders effective tradeoffs between bug detection efficiency and state space exploration cost, leading to critical execution paths to be overlooked. (2) Rule-based sequence mutation strategies suffer from path redundancy and inadequate guidance from contract logic, resulting in performance bottlenecks that stall the exploration of in-depth vulnerability-oriented paths. To tackle these challenges, we propose EchoFuzz, an LLM-guided fuzzing framework introducing Vulnerable Function Call Sequences (VFCS) - minimal, behavior-preserving execution paths that expose bugs through key state transitions. EchoFuzz consists of two key procedures. First, we develop a chain-guided LLM approach, that combines static analysis with logical understanding to generate contract-specific VFCS candidates that eliminate combinatorial redundancy. Second, we adopt an iterative fuzzing strategy that uses LLMs with real-time feedback to adaptively steer fuzzer toward uncovered branches. Experiments show EchoFuzz outperforms state-of-the-art methods, achieving 29\% higher branch coverage and detecting 62\% more vulnerabilities. It also found 37 previously unknown vulnerabilities in real contracts, showing strong practicality.

cs.SE↗

arXiv2026

Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations

Floorplans arise in many forms, from vector CAD drawings to raster renderings and sensor-derived density maps. This heterogeneity makes it difficult to build learning systems that transfer across modalities and support geometry-centric tasks such as alignment and retrieval. We introduce the Multimodal Floorplan Encoder (MMFE), which maps diverse 2D indoor representations into a shared dense latent grid. MMFE combines a frozen DINOv3 backbone with a trainable Dense Prediction Transformer (DPT) head, and is trained with a per-cell Information Noise-Contrastive Estimation (InfoNCE) objective that aligns spatially corresponding regions across modalities while using all other cells as negatives. To improve robustness to geometric distortions, we incorporate controlled similarity transformations and enforce geometric consistency through feature-grid warping. On Structured3D, a held-out out-of-domain dataset, MMFE improves cross-modal dense matching, enables robust similarity alignment with RANSAC, and yields strong retrieval when paired with learned aggregation.

cs.CV↗

arXiv2026

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deployed product where open-ended requests such as \emph{more NBA news} or \emph{less politics} steer subsequent feed recommendations rather than return a one-shot result list. Its agentic intent layer compiles explicit, inferred, negative, and compound intent into a grounded executable plan, then invokes conventional retrieval and optional semantic or multimodal reranking. The layer shares an intent-to-retrieval contract without requiring one model or serving path across search-like and recommendation-like modes. We evaluate Dear Algo under a precision-first objective. In a blinded audit of 300 public request-item pairs (296 evaluable), a strict categorical LLM-as-a-judge gate achieved 94.4\% exact-Relevant precision [88.8\%, 98.9\%]. Across 72 normalized request clusters, the full configuration produced 7.73 judge-qualified candidates per 20 slots versus 6.61 for an LLM-derived-query baseline, a gain of 1.11 [0.12, 2.12]. In a candidate-randomized serving-path study restricted to the reranker path's first 72 eligible hours, the user-weighted judge-Irrelevant share among judged admissions was 2.80\% versus 4.78\% off (-1.97 points [-3.02, -0.94]), while Exact-Relevant share was 2.24 points higher [0.08, 4.41]. Together, these studies show how explicit natural-language intent can be carried into feed recommendation under a precision-first evaluation framework

cs.AI↗

arXiv2026

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutions to achieve reasoning economy. By offering actionable insights and highlighting open challenges, we aim to shed light on strategies for improving the reasoning economy of LLMs, thereby serving as a valuable resource for advancing research in this evolving area. We also provide a public repository to continually track developments in this fast-evolving field.

cs.CL↗

arXiv2026

AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era

Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Existing evaluations largely assess it by asking models to generate ideas from a static, curated set of reference papers. That passive setup departs from the retrieval-and-reasoning workflow of modern AI scientists, and it becomes less discriminative as models improve. We introduce AgentIdeaBench, a multidisciplinary benchmark that evaluates scientific ideation under two matched settings, static observation and active exploration. We report matched Static-Active evaluations for 33 LLMs across 40 densely scored subfields spanning five disciplines, using a multidimensional, literature-verified scoring framework whose critics assess originality against retrieved prior art. Active exploration reveals considerably more capability headroom, and that headroom is unevenly distributed across models. Performance scales about twice as fast as under static observation, and the exploration gain is capability-gated, favoring the strongest models over the weakest. The gain reflects better grounding, improving feasibility, clarity, and specificity while leaving measured originality unchanged under our critics. We further explore Scientific World Modeling, a generation-time loop that refines a draft hypothesis through structured thought experiments. It benefits mid-capability models, and its impact diminishes among frontier models that appear to have internalized such reasoning patterns already. AgentIdeaBench gives future work on scientific ideation a measurement basis suited to the agent era.

cs.AI↗

arXiv2026

QROB: Quantifying Realization Overhead in Quantum Compilation via Reverse Construction

Quantum compilation reconciles a program's idealized interaction topology with hardware locality constraints, yet evaluations at scale lack calibrated references for realization overhead. We present QROB, a scalable reverse-construction methodology that generates compilation instances backward from directly realizable configurations, retaining the inverse paths as feasible, compiler-independent references. QROB provides a common evaluation substrate for NISQ SWAP routing and fault-tolerant lattice-surgery scheduling, while extending its reference-preserving principle to capacity-constrained quantum memory-access scheduling. Across systems ranging from 9 to 156 qubits, evaluations highlight QROB's utility as both a diagnostic benchmark and a data source. First, for compiler characterization, QROB reveals substantial realization gaps in existing tools, with NISQ compilers incurring up to 24.1x the reference SWAP cost and fault-tolerant compilers requiring up to 7.0x the reference makespan. Second, as a supervision source for data-driven compilation, a router trained on QROB references outperforms Qiskit SABRE on 84.8% of real-world application circuits. Finally, on real hardware, QROB reference realizations achieve a median mirror-circuit survival rate 1.65x that of full Qiskit O3 compilations across three 156-qubit IBM Heron-r2 processors, demonstrating that closing algorithmic compilation gaps translates directly into physical fidelity gains.

quant-ph↗

arXiv2026

Counting Beyond Instances: A Benchmark for Group-Individual Object Counting

Visual counting is commonly formulated at the instance level, aiming to estimate how many objects of a queried category appear in an image. However, real-world counting often involves higher-level semantic units formed by multiple instances, such as a bunch of grapes, a stack of plates, or a pair of shoes. This exposes a key limitation of existing counting formulations, which mainly focus on what to count, while largely overlooking at which semantic unit to count. We introduce Group-Individual Object Counting (GIC), a new setting that requires models to count both individual objects and semantic groups within a unified framework. To support this new task, we present BunchCount, a real-world benchmark with 1,330 images, 89,254 individual annotations, and 11,065 group annotations. BunchCount provides paired individual-group annotations within the same image and explicitly records containment relations between each group and its constituent individuals. Experiments on BunchCount show that current advanced counting models perform well on individual instances but fail to count semantic groups more accurately. To mitigate semantic granularity conflict, we propose a counting-unit guided relational counting framework, which exploits group-individual containment relations to regularize cross-granularity representations during training. Our method substantially improves group-level counting while better preserving individual-level counting ability, establishing a strong baseline for counting beyond instances.

cs.CV↗

arXiv2026

From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction

Temporal cascade prediction is widely studied, yet its empirical foundations remain fragile. Most existing works report results under random cascade splits that mix past and future signals, rely on datasets with limited features and no downstream conversion labels, and compare increasingly complex models without systematically examining whether benchmark conclusions are protocol-dependent. This paper argues that the field should move from leakage-prone evaluation toward fidelity-aware benchmarking. We introduce a protocol suite and renewed evaluation standard for temporal cascade prediction, centered on the Full Temporal protocol, overlap-based leakage diagnostics, and analyses of performance inflation and temporal drift. To broaden the scope of benchmark tasks, we also present Taoke, a real-world e-commerce cascade dataset with rich promoter/product features and observed purchase conversions, enabling both first-stage popularity forecasting and second-stage conversion forecasting under a shared benchmark asset. Finally, we include CasTemp as a lightweight reference method and additionally probe a larger same-task internal extension to verify that this pipeline remains operational at substantially greater scale. Together, these components turn cascade prediction from a protocol-sensitive leaderboard exercise into a more reliable analysis and benchmarking problem, while still providing a practical reference pipeline for large-scale evaluation and conversion-aware modeling.

cs.LG↗

arXiv2026

AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents

Long-term memory systems allow LLM agents to preserve information beyond a single context window, but most systems focus on storing and retrieving facts after extraction, leaving the write decision under-specified. What deserves memory can depend on the user's current task, topic, activity, or interaction partner, while uniform extraction applies one notion of importance across these different situations. We formulate this challenge as preference-conditioned write control and introduce AdaMem, which uses adaptive natural-language Memory Policies to personalize what an agent writes to memory. Each policy represents the user's memory preference for a particular interaction context, is updated from periodic feedback, and controls subsequent memory writing. We evaluate this loop in AdaMem-Bench, which assigns different memory preferences to six concurrent interaction personas across five ten-week stories. Across two extraction models and two feedback modes, AdaMem improves average QA accuracy over Mem0 from 80.0\% to 84.35\% while reducing persistent memory by 9.27\%. Our analyses show that explicit feedback helps models learn better memory policies, but current models still struggle to translate those policies into reliably selective writing behavior. AdaMem thus demonstrates the promise of adaptive write control while exposing policy execution as a central limitation of current memory agents. Our code is publicly available: https://github.com/galaxyChen/AdaMem

cs.CL↗

arXiv2026

LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation

Fixed benchmarks are costly to renew and cannot adapt their questions to model-specific failures. We ask whether LLMs can instead discover one another's weaknesses and turn those observations into an evaluation process. To study this question, we introduce \textbf{LivingArena}, an automated peer-probing framework in which models take turns testing one another. Using the interaction history, each questioner identifies potential weaknesses of its opponent and constructs targeted, verifiable questions to probe them. A 3,600-round tournament of ten models reveals a clear role asymmetry: strong answerers are not always reliable questioners, because they may generate internally inconsistent tests or fail to verify their own reference answers. After a questioner exposes an answerer's failure, it is more likely to pursue the same capability domain, while the answerer's weakness recurs on independently generated questions, including questions written by different models. These findings show that peer probing can reveal persistent model-specific weaknesses while separately evaluating answering and reliable test construction. By automating this process and allowing test difficulty to evolve with model capabilities, LivingArena provides a "living" benchmark for model development, red-teaming, and capability-aware multi-agent coordination. We publicly release our code: https://github.com/galaxyChen/LivingArena

cs.AI↗

arXiv2026

AceSpec: An Asymmetric Edge-Cloud Collaborative Framework for Communication-Efficient LLM Inference

Deploying Large Language Models (LLMs) on edge devices typically relies on model compression or split inference. However, compression degrades reasoning capabilities, while split inference suffers from severe Wide Area Network (WAN) communication bottlenecks. Edge-cloud speculative decoding emerges as a promising alternative, leveraging an edge small model to draft tokens for cloud verification. Yet, over volatile WANs, inevitable prediction rejections trigger catastrophic pipeline stalls and network-wide rollbacks, neutralizing collaborative gains. To overcome this, we propose AceSpec, an asymmetric edge-cloud collaborative framework. AceSpec utilizes un-saturated edge compute to proactively construct a probabilistic state cache, effectively transforming network-wide pipeline flushes into $\mathcal{O}(1)$ local memory lookups. To preserve bandwidth, it employs an asymmetric communication protocol that transmits minimal main-chain indices uplink and compact sparse distributions downlink. Furthermore, we introduce a network-aware, Lagrangian-optimized resource allocation strategy that dynamically maximizes the local cache hit rate. Evaluations demonstrate that AceSpec achieves up to a 3.52$\times$ throughput speedup and exhibits exceptional bandwidth immunity, sustaining near-peak inference performance even under severely constrained 50 Kbps WAN conditions.

cs.DC↗

arXiv2026

Effective Range and Optimal Frequency of Through-the-Earth Magnetic Induction Communication

Magnetic induction communication (MIC) is a promising technology for through-the-earth (TTE) communication. Previous studies on the MIC range have often overlooked the impact of eddy losses caused by underground materials. For TTE MIC, significant eddy losses complicate the analysis of the effective MIC range, which is vital for optimizing performance but has never been addressed in the literature. Accounting for the conductivity and permittivity of the underground medium, this paper derives the effective MIC range in TTE MIC, along with a closed-from expression that predicts the optimal carrier frequency to maximize this range. Finite element simulations validate the analysis, demonstrating that the optimal carrier frequency can significantly enhance the MIC range. It is also revealed that optimizing the antenna radius is effective in extending the MIC range for TTE and vehicle MIC applications.

eess.SY↗

arXiv2026

Bias-Preserving Gates and Quantum Error Correction With Dual-Rail Cat Codes

Scalable fault-tolerant quantum computation requires quantum error-correcting codes that simultaneously support universal logical operations, suppress hardware-specific noise, and enable efficient handling of photon-loss errors. Bosonic encodings such as the dual-rail and cat codes each offer attractive features but also exhibit important limitations when used in isolation. The dual-rail code enables efficient single-photon-loss detection by converting leakage out of the computational subspace induced by photon-loss errors into an erasure error. In contrast, the cat code provides a resource-efficient, bias-tailored error-correction scheme with bias-preserving logical gate operations. Here, we introduce the dual-rail cat code (DRCC), a concatenated bosonic encoding that combines an inner cat code with an outer dual-rail structure, thereby inheriting and enhancing the advantages of both constituent codes. We analyse the error-correction properties of the DRCC and propose a deterministic single-photon-loss correction protocol by concatenating it with an outer repetition code. Exploiting the code's intrinsic noise bias, we construct a universal set of logical gates using only beam-splitter interactions and demonstrate that all logical operations preserve the erasure-biased noise structure. The DRCC offers several distinctive advantages, including the absence of relative geometric phases during gate operations, deterministic erasure detection and correction, and simultaneous syndrome extraction without interrupting stabilisation. These features make the DRCC a promising bosonic code for hardware-efficient, bias-preserving, and erasure-resilient fault-tolerant quantum computation.

quant-ph↗

arXiv2026

Agent2UCB: Agentic System for Generative Engine Optimization

Large language model driven search engines such as Google AI Overviews and Perplexity have created new opportunities for Generative Engine Optimization (GEO) the practice of refining content to increase its likelihood of being cited or summarized by generative systems. We demonstrate Agent2UCB, an agentic GEO system that autonomously improves content visibility through customized, feedback-driven optimization. For each content item, the system evaluates nine GEO strategies, identifies the most effective method, and accelerates selection using a bandit-based Agent2UCB policy that integrates LLM priors with online reward signals. To monitor side effects, the system also provides a lightweight, text-only SEO readiness evaluation covering readability, topical coverage, and EEAT-style credibility. Experiments on GEO-Bench show consistent visibility gains while preserving SEO quality. The demo allows users to choose the websites of interest, observe the optimization workflow, and compare GEO/SEO outcomes across methods.

cs.AI↗

arXiv2026

The Adaptive Solution of High-Frequency Helmholtz Equations via Multi-Grade Deep Learning

The Helmholtz equation is fundamental for modeling wave propagation in acoustics, electromagnetics, and geophysics; however, high-frequency regimes remain notoriously difficult due to the severe numerical ``pollution effect.'' We propose FD-MGDL, an adaptive framework that synergizes finite difference discretizations with Multi-Grade Deep Learning (MGDL) to efficiently resolve high-frequency wavefields. Unlike standard physics-informed neural networks (PINNs), which frequently suffer from spectral bias and heavy automatic differentiation overhead, FD-MGDL employs a progressive, grade-wise training strategy that incrementally incorporates shallow sub-networks to refine residual errors. By leveraging ReLU activations in refinement grades, the framework reformulates the highly non-convex global optimization problem into a sequence of tractable convex subproblems, dramatically improving training stability and convergence reliability. Extensive numerical experiments in two and three dimensions with wavenumbers up to $κ=200$ demonstrate that FD-MGDL significantly outperforms single-grade networks and standard benchmark neural solvers in both accuracy and computational efficiency. When applied to an inhomogeneous concave velocity model, the proposed method accurately captures wave focusing and caustic formations, markedly outperforming classical five-point finite difference schemes in resolving sharp phase transitions and peak amplitudes. These results establish FD-MGDL as a robust, scalable, and mathematically grounded paradigm for high-frequency wave simulation in complex media.

math.NA↗

arXiv2026

ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting

Understanding object dynamics requires not only predicting future trajectories but also examining whether a model captures the physical properties that govern motion. However, existing benchmarks rarely expose object-level physical properties as explicit evaluation targets alongside trajectory forecasting. To address this gap, we introduce \emph{ExPhy}, a multi-object trajectory forecasting benchmark containing 24,000 simulated physical scenes with explicit object-level labels for mass, friction, and restitution. ExPhy provides observed and future trajectories together with an in-distribution (ID) split and two out-of-distribution (OOD) splits over physical parameters (OOD-Parameter) and initial states (OOD-Initial) for jointly evaluating trajectory forecasting and physical property estimation. We further instantiate \textsc{PhyODE}, a physics-guided model with an explicit property interface that estimates physical properties from observed trajectories and uses them for differentiable future rollout. On the long-horizon OOD-Initial setting, \textsc{PhyODE} reduces ADE and FDE by 33.1\% and 31.0\%, respectively, compared with the strongest baseline. Zero-shot evaluation on ComPhy further assesses cross-benchmark transfer. Property-level analyses reveal that accurate trajectory forecasting does not necessarily imply accurate recovery of the underlying physical properties. Code and data are available at https://github.com/Zest86/ExPhy.

cs.AI↗