Searcharxiv⌕ Search

arXiv subjects

Yong Yu

Publications and source records attributed to Yong Yu.

At least 37 records · Page 2Linked to original sources
arXiv2026

A unified framework for determining transition dipole polarization in solid-state spin defects

Spin-photon interfaces based on solid-state defects are key building blocks for scalable quantum networks and hybrid quantum platforms. Optimizing light-matter coupling in these systems requires precise knowledge of the optical transition dipole polarization, yet for many promising quantum emitters this quantity is hard to determine and therefore remains poorly characterized. Here, we develop a framework for reconstructing electric transition dipole polarization in spin-1/2 solid-state defects directly from ensemble spectroscopy. The approach combines the response of photoluminescence spectra to magnetic field, optical polarization, and strain. Applied to erbium ions in silicon, a particularly challenging system containing multiple crystallographic subsites, the framework identifies strain-induced shifts as the origin of asymmetric ensemble spectra and enables simultaneous determination of the optical dipole polarization and strain-orbital coupling tensor. The resulting model predicts how cavity-ion coupling depends on crystallographic orientation and magnetic-field direction, which we verify using single erbium ions coupled to a nanophotonic cavity. Together, these results establish a broadly applicable route for extracting microscopic properties of solid-state quantum emitters from ensemble spectroscopy and for engineering optimized spin-photon and spin-phonon interfaces.

quant-ph↗
arXiv2026

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation

Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided evidence. Reinforcement learning (RL) is a promising direction for hallucination mitigation, but response-level faithfulness rewards suffer from a granularity mismatch: localized hallucinations can cause supported content to receive spurious penalties. Although recent work introduces fine-grained feedback such as claim-level verification and token-level rewards, unbalanced credit assignment can still induce length, verbosity, or optimization-noise biases. We propose BALTO, a Balanced Token-level Policy Optimization framework for hallucination mitigation. BALTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels. A balanced token-level credit assignment mechanism is introduced into the framework. This design redistributes probability mass from unsupported content toward faithful content, rather than suppressing the entire response. We systematically analyze the limitations of response-level rewards from a theoretical standpoint, and prove BALTO's advantages in training stability and optimization efficiency for hallucination mitigation. Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings and consistently outperforms existing post-training baselines in Q-Score, demonstrating a stronger faithfulness--informativeness trade-off.

cs.CL↗
arXiv2026

MOTOR: Learning ID-free Item Representation with Token Crossing for Embedding-based Multimodal Recommendation

While multimodal recommendation models have effectively integrated visual and textual information, their reliance on unique ID embeddings constitutes a fundamental performance bottleneck. Specifically, ID-based paradigms suffer from three limitations: (1) \textbf{Information Isolation}, where unique IDs prevent semantic information exchange among related items; (2) \textbf{Cold-Start Vulnerability}, as ID embeddings are difficult to optimize with sparse interactions; and (3) \textbf{Storage Inefficiency}, where parameter costs scale linearly with item quantity. To overcome these challenges, we propose \textbf{MOTOR}, a novel \textbf{ID-free MultimOdal TOken Representation} scheme. MOTOR replaces explicit item IDs with learnable, shared multimodal tokens, fundamentally transforming the recommender into an ID-free framework. Methodologically, we first employ product quantization to discretize raw multimodal features into compact token IDs. These tokens serve as implicit item features, which are then synthesized via a novel \textbf{Token Cross Network (TCN)} to capture high-order interaction patterns. This "discretize-and-interact" mechanism enables semantic sharing across items and significantly compresses the model size without introducing complex auxiliary losses. Extensive experiments across nine mainstream models demonstrate the significant performance improvement achieved by MOTOR. Further, MOTOR improves the capability of these models to recommend items in cold-start scenarios.

cs.IR↗
arXiv2026

DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation

Cold-start item recommendation remains a persistent challenge in real-world systems due to the absence of interaction histories. While prior models attempt to bridge this gap using item content features, they universally suffer from the \textbf{seesaw dilemma}: enhancing performance for cold items inevitably degrades performance for warm items, and vice versa. We identify that this dilemma stems from a fundamental \textbf{distributional disparity}: warm item embeddings occupy a complex ``behavioral manifold" shaped by rich interaction signals, whereas cold item embeddings are constrained to a ``semantic manifold" derived solely from auxiliary content. Existing methods often force a rigid mapping between these inconsistent spaces, causing the model to sacrifice the precision of warm representations to accommodate cold ones. To address this, we propose \textbf{DiffCold}, a diffusion-based generative model that unifies warm and cold representations. Unlike GANs or VAEs, DiffCold leverages conditional diffusion to reconstruct warm item embeddings from content, preserving the underlying manifold structure without degradation. We further tailor this paradigm with two specific designs: a \textbf{Retrieval-enhanced Aggregator} that initializes generation using semantically similar warm items to bypass inefficient noise, and a \textbf{Simulation-based Representation Alignment} module that enforces distribution consistency between generated and real embeddings via contrastive learning. Experiments on three benchmarks confirm that DiffCold resolves the seesaw dilemma, consistently outperforming state-of-the-art methods across all metrics.

cs.IR↗
arXiv2026

SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web

The Agentic Web is emerging as a paradigm in which autonomous software agents interact with online resources and with each other to accomplish user goals. However, the capacity of Agentic Web is still limited by insufficient autonomous software agent population, which has become a crucial challenge for scaling Agentic Web. In order to alleviate this, we study the task of automatically converting existing code repositories into autonomous software agents via coding agents, decompose the process into critical stages, and identify key technical hurdles. To systematically evaluate this capability, we propose SoftWare Agent generation for Agentic Web Bench (SW-$A^2$-Bench), the first benchmark designed for software agent generation. SW-$A^2$-Bench evaluates not only whether software agents can be generated, but also whether generated software agents are faithful to the source repositories and interoperable with other agents in multi-agent workflows. Our experiments demonstrate that our approach effectively activates the functional capabilities of code repositories and enables interoperable multi-agent collaboration in Agentic Web. We believe that this work will provide a standardized evaluation for software agent generation and will contribute to the future of scaling the capacity of Agentic Web.

cs.MA↗
arXiv2026

Infinitesimal Bialgebra on Planar Binary Trees

We construct a weight-zero infinitesimal bialgebra structure on the $\bk$-module spanned by planar binary trees, using the under product $\backslash$ of Aguiar--Sottileand a root-recursive coproduct $\DeltaLR$. We prove that $\DeltaLR$ is coassociative and satisfies the infinitesimal derivation rule with respect to $\backslash$, hence gives a unitary infinitesimal bialgebra distinct from the usual Loday--Ronco Hopf structure. We also obtain an elementary vertex-cut formula, establish freeness properties for unitary $(\backslash,\vee)$-algebras and unitary infinitesimal $(\backslash,\vee)$-bialgebras, and identify the construction with the infinitesimal coproduct transported from planar rooted forests.

math.CO↗
arXiv2026

MMSkills: Towards Multimodal Skills for General Visual Agents

Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however, procedural knowledge is inherently multimodal: reuse depends not only on what operation to perform, but also on recognizing the relevant state, interpreting visual evidence of progress or failure, and deciding what to do next. We formalize this requirement as multimodal procedural knowledge and address three practical challenges: (I) what a multimodal skill package should contain; (II) where such packages can be derived from public interaction experience; and (III) how agents can consult multimodal evidence at inference time without excessive image context or over-anchoring to reference screenshots. We introduce MMSkills, a framework for representing, generating, and using reusable multimodal procedures for runtime visual decision making. Each MMSkill is a compact, state-conditioned package that couples a textual procedure with runtime state cards and multi-view keyframes. To construct these packages, we develop an agentic trajectory-to-skill Generator that transforms public non-evaluation trajectories into reusable multimodal skills through workflow grouping, procedure induction, visual grounding, and meta-skill-guided auditing. To use them, we introduce a branch-loaded multimodal skill agent: selected state cards and keyframes are inspected in a temporary branch, aligned with the live environment, and distilled into structured guidance for the main agent. Experiments across GUI and game-based visual-agent benchmarks show that MMSkills consistently improve both frontier and smaller multimodal agents, suggesting that external multimodal procedural knowledge complements model-internal priors.

cs.AI↗
arXiv2026

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval

Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-horizon inference loops, leading to high inference cost and limited suitability for time-sensitive news retrieval. We propose DynaTree, a two-stage framework for efficient and adaptive news retrieval. In the offline stage, DynaTree uses coordinated agents to construct a reusable retrieval tree that materializes the semantic space of a query topic. In the online stage, DynaTree performs lightweight daily subtree selection over a time-localized evaluation proxy, without further agentic reasoning, tree modification, or retraining. Experiments on a multi-day Syft news benchmark and multiple BEIR datasets show that DynaTree achieves strong recall and ranking performance, consistently outperforming standard RAG and prior agentic baselines. We further deploy DynaTree in the Syft production system and evaluate it through online A/B testing from Jan. 28 to Feb. 6, 2026. The dynamically adapted variant improves survival rate from 0.32-0.53 to 0.59-0.73 over a fixed offline-selected subtree and outperforms existing production recallers on every evaluation day. These results show that persistent, structure-aware semantic expansion can translate offline agentic reasoning into practical improvements in coverage, freshness, and relevance for real-world news retrieval.

cs.IR↗
arXiv2026

Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between interactions is largely wasted, leaving agents unable to prepare for future user needs. To bridge this gap, we introduce ProAct, a proactive agent architecture that leverages idle-time compute to anticipate and fulfill likely upcoming user needs. By analyzing evolving dialogue history together with persistent memory, ProAct predicts upcoming needs and iteratively acquires information, allowing the agent to resolve knowledge gaps and prepare evidence before the user initiates a query. To rigorously evaluate proactive capabilities, we also introduce ProActEval, a comprehensive benchmark comprising 200 scenarios across 40 domains, featuring predictable need chains and diverse user cognitive profiles. Empirical results demonstrate significant advantages over reactive baselines. ProAct accelerates task completion by reducing required turns by 14.8%, decreases user effort by 11.7%, and cuts hallucination rates by 28.1% on ProActEval. Furthermore, MemBench evaluations confirm that ProAct achieves state-of-the-art reflective accuracy, underscoring its sustained and robust performance.

cs.CL↗
arXiv2026

A Gaia-linked High-purity QSO Candidate Catalog in Selected Fields with Extinction-binned Calibration and Spectrum-informed Training

We present an extinction-calibrated, Gaia-source-level QSO candidate catalog for selected fields, designed as a high-purity input catalog for fiber-spectroscopic follow-up rather than as an all-sky QSO census. The deployed selector uses Gaia astrometry and photometry, optical/infrared catalog features, and E(B-V)-binned threshold calibration; spectra are used only during training via a source-grouped spectrum-teacher model. The sample definition is layered: a four-field core domain ladder provides the main validation baseline, four application/stress-test fields probe portability, and COSMOS is treated separately as an Extreme Deep boundary case. At the recommended conservative operating point, calibrated to a validation-set purity of 0.98, the P3 spectrum-informed catalog selector achieves a measured test-set purity of 0.9809 and a spectroscopic-label completeness of 0.8869 within the frozen Gaia-linked benchmark, whereas the Gaia official QSO probability yields a spectroscopic-label completeness of 0.4493 under the same threshold protocol. The evaluation protocol excludes downstream validation/test Gaia source IDs from teacher fitting and checkpoint selection, and uses teacher probabilities only for downstream training rows. Relative to the earlier P2 teacher, P3 yields a modest mean completeness gain across five seeds, with a small decrease in purity and a small increase in false positives; the gain is most evident in higher-extinction and faint-source diagnostics. The released product is a catalog and empirical selection-function data product with source identifiers, field-layer assignments, input-coverage flags, calibrated scores, threshold flags, validation metadata, and provenance/QC fields. In COSMOS, the Gaia-linked parent set is much shallower than COSMOS2020; the robust 39-object subset is interpreted as a purity-oriented priority list rather than a completeness measurement.

astro-ph.IM↗
arXiv2026

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. However, we identify a pervasive length bias in existing PRMs: they tend to assign higher scores to longer reasoning steps, even when the semantic content and logical validity are unchanged. This bias undermines the reliability of reward predictions and leads to overly verbose outputs during inference. To address this issue, we propose CoLD(Counterfactually-Guided Length Debiasing), a unified framework that mitigates length bias through three components: an explicit length-penalty adjustment, a learned bias estimator trained to capture spurious length-related signals, and a joint training strategy that enforces length-invariance in reward predictions. Our approach is grounded in counterfactual reasoning and informed by causal graph analysis. Extensive experiments on MATH500 and GSM-Plus show that CoLD improves accuracy in step selection, and encourages more concise, logically valid reasoning. Furthermore, it consistently improves downstream RL performance and generalizes across domains by mitigating length bias, demonstrating CoLD's strong generalization capability.

cs.CL↗
arXiv2026

Planar Degenerate Anchoring in Landau-de Gennes Energy

The aim of this article is twofold. First, in the large-body limit and when the temperature is below the nematic-isotropic transition threshold, we verify that the $\mathbb{S}^2$-valued energy-minimizing harmonic map on a bounded smooth domain $Ω\subset \mathbb{R}^3$ with tangential boundary condition is a singular limit of the Landau-de Gennes energy minimizers subject to the Fournier-Galatola planar degenerate anchoring [22]. This harmonic map is referred to as the canonical harmonic map. Our second aim is to address the local structure of the canonical harmonic map near the boundary singularities, which we call boojums. We show that the tangent map of the canonical harmonic map near a boojum is uniquely characterized by a half bubble with a hedgehog or an anti-hedgehog structure, up to a planar rotation. Comparing to the interior counterpart studied by Brezis-Coron-Lieb in [7], for which the full SO(3) group action can be applied to the tangent map near an interior singularity, we can only apply planar rotations to the tangent map near a boojum to maintain the tangential boundary condition. The degeneracy of the group action from SO(3) to SO(2) makes it challenging to investigate the local structure of the boojum singularity. On the other hand, the boundary condition for the half bubble is Dirichlet on the curved boundary and tangential on the flat boundary. We need to extend the Schoen-Uhlenbeck bubbling analysis in [45,46] for energy-minimizing harmonic maps with Dirichlet boundary conditions to our current case with the mixed-type boundary conditions.

math.AP↗
arXiv2026

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning

With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. Most of these works utilized DMs to sample directly from the trajectory space, where DMs can be viewed as a combination of dynamics models and policies. In this work, we explore how to decouple DMs' ability as dynamics models in fully offline settings, allowing the learning policy to roll out trajectories. As DMs learn the data distribution from the dataset, their intrinsic policy is actually the behavior policy induced from the dataset, which results in a mismatch between the behavior policy and the learning policy. We propose Dynamics Diffusion, short as DyDiff, which can inject information from the learning policy to DMs iteratively. DyDiff ensures long-horizon rollout accuracy while maintaining policy consistency and can be easily deployed on model-free algorithms. We provide theoretical analysis to show the advantage of DMs on long-horizon rollout over models and demonstrate the effectiveness of DyDiff in the context of offline reinforcement learning, where the rollout dataset is provided but no online environment for interaction.

cs.LG↗
arXiv2026

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System

Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create organization bottlenecks, context pressure, and mis-specialization. We present SkillMAS, a non-parametric framework for adaptive specialization in multi-agent systems that couples skill evolution with MAS restructuring. SkillMAS uses Utility Learning to assign credit from verified execution traces, bounded skill evolution to refine reusable procedures without unfiltered library growth, and evidence-gated MAS restructuring when retained failures and Executor Utility indicate a structural mismatch. Across embodied manipulation, command-line execution, and retail workflows, SkillMAS is competitive under the reported harnesses while clarifying how post-deployment specialization is attributed, updated, and applied.

cs.MA↗
arXiv2026

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \textbf{Neural Collaborative Context Engineering (NCCE)}, a framework that transitions optimization from a static global search to dynamic, instance-wise routing. NCCE first bootstraps a diverse catalog of anchor contexts and then employs a novel \textbf{Context-CF Co-Evolution} mechanism. This stage establishes a synergistic feedback loop: a lightweight Neural Collaborative Filtering (NCF) model learns instance-context preferences to guide the generation of specialized context variants, while the newly evaluated contexts continuously refine the NCF model's understanding of latent preferences. At inference time, the trained NCF model acts as a context router, dynamically assigning the most suitable context strategy to each unseen instance. Theoretical Proofs and comprehensive experiments demonstrate that by matching individual inputs with their optimal contexts, NCCE significantly improves task accuracy, highlighting the critical importance of personalization in LLM context engineering.

cs.CL↗
arXiv2026

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle

As autonomous code agents move toward end-to-end software development, evaluating their practical autonomy becomes critical. Current benchmarks hide friction by testing agents in pre-configured environments, and their static evaluation pipelines frequently fail when parsing fully autonomous trajectories. We address these limitations with SWE-Cycle, a benchmark of 489 rigorously filtered instances. SWE-Cycle evaluates agents across three isolated tasks, including environment reconstruction, code implementation, and verification test generation, as well as an end-to-end FullCycle task that integrates all three. The FullCycle task requires agents to work autonomously in a bare repository without human scaffolding. To reliably assess these complex execution paths, we developed SWE-Judge. By combining static code review with dynamic testing, this execution-capable evaluation agent accurately verifies functional correctness and eliminates the systematic measurement errors of traditional static parsers. We evaluate code agents powered by six state-of-the-art LLMs across these four tasks. The results reveal a sharp drop in solve rates when transitioning from isolated tasks to FullCycle execution, exposing critical bottlenecks in handling cross-phase dependencies and maintaining code quality. Together, SWE-Cycle and SWE-Judge provide a comprehensive framework for accurately measuring the end-to-end capabilities of autonomous software agents.

cs.SE↗
arXiv2026

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents

The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerability. This position paper characterizes a new systemic threat we term Agentic Denominator Gaming, in which a malicious actor deploys AI agents to generate and submit a large volume of superficially plausible but low-quality papers. Crucially, their objective is not the acceptance of low-quality papers, but rather to inflate the submission denominator and overwhelm reviewing capacity. Under a relatively stable acceptance rate, this dilution can systematically increase the publication probability of a small, targeted set of legitimate papers. We analyze the practical feasibility of this threat and its broader consequences, including intensified reviewer burnout, degraded review quality, and the emergence of industrialized automated agent mills. Finally, we propose and evaluate a range of mitigation strategies, and argue that durable protection will require system-level policy and incentive reforms, rather than relying primarily on technical detection alone.

cs.CL↗
arXiv2026

Development of a quadripartite wakefield structure as dechirper for free electron laser

Wakefield structures are critical for beam manipulation in free-electron lasers (FELs), particularly when serving as dechirpers, where beam-induced longitudinal wakefields compensate the energy chirp introduced during beam magnetic compression. However, conventional planar structures also generate time-dependent quadrupole wakefields due to their asymmetric geometry, which can cause beam mismatch and projected emittance growth. To address this limitation, we propose a quadripartite wakefield structure comprising four identical corrugated plates, able to fully suppress quadrupole wakefields while preserving strong longitudinal wakefields. To accurately evaluate its performance, we calculate wake potentials based on the Panofsky-Wenzel theorem using three-dimensional simulation software and extract the corresponding wake functions by deconvolution. We further adopt a particle-to-particle (P2P) tracking method incorporating these wake functions, which is capable of accounting for higher-order components and nonlinear effects that are typically neglected in standard tracking codes. Simulation results confirm that the quadripartite geometry offers significantly reduced projected emittance growth and a 25% shorter structure length compared with the planar design. The tracking method also reveals that the nonlinearities of three-dimensional wakefields induce noticeable slice emittance growth for large transverse beam sizes, which may in turn affect lasing performance. In addition, the tracking method enables analysis of various types of assembly error and indicates that misalignment along the direction of plate motion may severely degrade the emittance via dipole wakefields. Such misalignment can be mitigated through beam-based alignment and precise plate adjustment using high-resolution servo motors.

physics.acc-ph↗