arXiv subjects

Lu Chen

Publications and source records attributed to Lu Chen.

At least 73 records · Page 4Linked to original sources

arXiv2026

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.

cs.AI↗

arXiv2026

XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflows

LLM-based multi-agent systems increasingly coordinate planning, reasoning, tool use, and human interaction, yet their reliability remains limited. A central source of this limitation is the underspecified prompt--harness boundary. Current systems lack a principled way to decide which workflow commitments should remain in prompts and which should become harness structure. We present \textbf{XFlow}, an executable protocol programming system for reliable multi-agent workflows, and \textbf{XPF} (XFlow Protocol Format), its domain-specific protocol programming language. XFlow occupies a middle position between prompt-only orchestration and markup-like workflow descriptions. XPF remains readable as a literate protocol, but it is compiled and executed as a program. Its design keeps informal semantic work inside actors while moving selected commitments into harness structure that can be checked, preserved, and enforced. At runtime, XFlow stages uncertainty through lifecycle-governed symbols, which are typed state cells with validation and commit states. Actor outputs are mediated before they become shared state, instead of spreading through prompts, transcripts, or implicit memory. Our experiments cover Constrained Interaction, Long-Context Reasoning, and Agentic Software Engineering. They show that XFlow improves reliability by making constraints, evidence handling, and process requirements explicit and enforceable.

cs.PL↗

arXiv2026

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment

Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes. Creations by generative models may contain artifacts, implausible details, or stylistic drift away from photorealism and offer little insight into why an edit was made. We propose IEA, a conversational Image Editing Agent that learns to operate parameterized tools in an explicit, interpretable action space. IEA is trained via a three-stage multitask pipeline: (1) SFT on distilled expert edits, (2) GRPO with rewards for likeness improvement, tool usefulness, and intent summarization, and (3) large-scale synthetic fine-tuning to jointly master image editing, refinement, and user intent summarization. By manipulating 16 editing tools step by step, IEA produces transparent edit traces that can be inspected and debugged. In quantitative experiments, it attains a lower pixel distance on the edit task and a higher ROUGE-L on the summary task than strong baselines. In user studies, it ranks best among tool-calling methods for instruction following while surpassing generative methods in overall perceptual quality. Our results validate interpretable, tool-centric VLMs as a reliable path to human instruction-guided image retouching.

cs.CV↗

arXiv2026

Bulk Superconductivity driven by Disorder-Induced Delocalization in 4Hb-Ta(S$_{1-x}$Se$_x$)$_2$

The unconventional superconductor 4Hb-TaS$_2$ is a natural heterostructure that can be broadly understood as interleaving Mott-like and metallic layers. We study the properties of this material as a function of quenched disorder in the form of Se/S substitution and find that while disordered samples show bulk superconductivity, clean samples do not. We show that a disorder-driven delocalization of carriers in the Mott-like ($1T$-) layer forms a new Fermi surface that is absent in the cleanest samples. This suggests that one of the primary drivers for superconductivity is the fragility of the Mott state, whose delocalization brings to life a sea of strongly correlated electrons.

cond-mat.supr-con↗

arXiv2026

When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training

Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Recent group-based methods such as GiGPO improve over GRPO by constructing step-level advantages at repeated anchor states. However, we show that such dense credit can be statistically unreliable: under limited rollouts, rare but lucky actions may receive overly large advantages, producing divergent anchor bias and late-stage training oscillation. We propose Evidence-Calibrated Policy Optimization (ECPO), a critic-free policy optimization algorithm that calibrates step-level credit before policy updates. ECPO combines Evidence-Calibrated Action Advantage, which groups rollouts by canonical actions and shrinks low-count estimates, with Variance-Gated Credit Weighting, which suppresses anchor states dominated by within-action noise. Experiments on ALFWorld and WebShop with Qwen2.5-1.5B/7B show that ECPO consistently outperforms strong baselines, improving GiGPO by +5.2/+7.3 success points on ALFWorld/WebShop with Qwen2.5-1.5B while adding only 0.1% additional advantage-computation overhead.

cs.LG↗

arXiv2026

OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields

As multimodal language models play an increasingly important role in scientific research, materials science offers a critical testbed due to its interdisciplinary, multimodal, and application-driven nature. However, existing materials benchmarks mainly focus on property prediction, knowledge QA, or characterization understanding, leaving the broader reasoning process from materials knowledge to application underexplored. To fill this gap, we present OmniMatBench, a human-calibrated multimodal reasoning benchmark for materials science. OmniMatBench contains 3,171 expert-curated QA and calculation problems across 19 materials-science subfields, spanning fundamental materials knowledge, structural and engineering materials, materials processing and manufacturing, and functional and applied materials. We evaluate 13 open-source and closed-source MLLMs and find that the best model achieves only a 0.372 overall score, revealing a substantial gap in current materials-science reasoning. Further analysis shows strong variation across subfields, fixed reasoning heuristics, uneven materials knowledge, and limited high-level knowledge application under formula-, retrieval-, and code-assisted settings. OmniMatBench provides crucial insights into the capabilities and limitations of current MLLMs and establishes a foundation for reliable AI assistants in materials-science research.

cs.AI↗

arXiv2026

Liouville theorems for $p$-Laplacian equations in convex cones without finite-energy condition

We study the anisotropic Finsler $p$-Laplacian equation \begin{equation*} \left\{ \begin{aligned} &-Δ^{H}_{p}u=f(u) \quad\,\,\, &{\rm{in}} \,\, \mathcal{C}, &{\bf{a}}(\nabla u)\cdot ν=0 \quad\,\,\, &{\rm{on}} \,\, \partial\mathcal{C}, \end{aligned} \right. \end{equation*} where $N\geq3$, $1<p<N$, $\mathcal{C}\subseteq\mathbb{R}^{N}$ is an open convex cone and $Δ^{H}_{p}$ is the anisotropic Finsler $p$-Laplacian operator. If $f(u)$ is nonnegative and subcritical, we prove that every bounded nonnegative solution in $\mathcal{C}$ is identically zero. In particular, for $f(u)=u^{q}$ with $0<q<p^*-1$, we establish a pointwise decay estimate in $\mathcal{C}$ via the doubling argument and blowing-up method and prove that all nonnegative solutions must be zero without the boundedness assumption. Our results are the subcritical counterpart of the classification result for the critical case in \cite{CFR}, and extend the Liouville type theorems in $\mathbb{R}^{N}$ for the standard $p$-Laplacian in \cite{SZ} and for the anisotropic $p$-Laplacian in \cite{CFV, CHN} to general convex cones $\mathcal{C}$. In the critical case $f(u)=u^{p^*-1} $ and typical case $H(ξ)=|ξ|$, for $\frac{N+1}{3}<p<N$, we classified the positive solutions of the critical $p$-Laplacian equation in convex cones $\mathcal{C}$ without finite-energy assumption. This extends the classification result of \cite{Ou} in $\mathbb{R}^{N}$ to general convex cones $\mathcal{C}$, and removes the finite-energy assumption in \cite{CFR} in the typical case $H(ξ)=|ξ|$.

math.AP↗

arXiv2026

Understanding the Rising Human-AI Affective Bonding: Conceptualization and HAABI Scale Development

As conversational AI becomes capable of sustained, affectively responsive interaction, users may form bonds beyond instrumental use. Existing measures often adapt interpersonal frameworks or focus on specific relational outcomes, leaving limited tools for assessing human-AI affective bonding on its own terms. Across two studies, we developed and validated the Human-AI Affective Bonding Inventory (HAABI). Study 1 used thematic analysis of semi-structured interviews with 52 emotionally engaged conversational AI users to identify cognitive, emotional, and behavioral features of bonding. Study 2 translated these insights into a self-report inventory and validated it among 673 Chinese conversational AI users. Exploratory and confirmatory factor analyses supported a 20-item, four-factor structure: emotional realism, separation anxiety, emotional investment, and romantic intimacy. The HAABI showed good reliability, construct validity, and known-groups validity. The scale therefore provides a neutral, user-centered tool for studying how affective bonds with conversational AI are formed, experienced, and related to users' psychological outcomes.

cs.HC↗

arXiv2026

RTP-LLM: High-Performance Alibaba LLM Inference Engine

Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users. RTP-LLM addresses fundamental bottlenecks through integrated design. It optimizes model loading via file-order-driven I/O and parallel I/O-communication overlapping. The Prefill-Decode Disaggregation architecture decouples compute-intensive prefill from memory-bound decode phases, combined with hierarchical multi-tiered KV cache management enabling efficient cache reuse. In addition, RTP-LLM incorporates modular speculative decoding supporting multiple algorithms, adaptive KV cache quantization, and decoupled multimodal processing, with support for multi-level parallelism. Comprehensive evaluations across diverse model architectures (8B-235B parameters) have been conducted, where both controlled benchmarks and real production workloads are used. The results demonstrate RTP-LLM's superior performance against vLLM and SGLang: 4.7x-6.3x model loading speedup, 35-37% TTFT P95 latency reduction with 215% cache reuse improvement in production traffic scheduling, 1.12x-2.48x and 1.86x-2.52x throughput improvements in speculative decoding and multimodal inference, respectively, and 35-40% batch latency reduction with 1.9x-3.0x TTFT improvement in quantized inference. RTP-LLM's production-proven architecture and open-source availability make it a comprehensive solution for industrial LLM deployment.

cs.OS↗

arXiv2026

Determining evolutionary equations from a single passive boundary observation

We study inverse boundary problems for evolutionary PDEs using only a single passive boundary observation, where data from an unknown internal source propagate through an unknown medium without active inputs. The goal is the simultaneous recovery of coupled unknowns (sources and coefficients) from severely limited data. Unlike active methods with rich, structured inputs, passive observation poses two core challenges: minimal information and intrinsic coupling of multiple unknowns. Consequently, such problems remain largely open and unsystematically studied. We develop a unified framework based on integral identities, harmonic and microlocal analysis, and low-/high-frequency asymptotics. This approach yields the first systematic resolution for second-order hyperbolic, parabolic, and Schrödinger equations under a single coherent method. The key condition requires the measurement dataset's cardinality to exceed the unknowns' by at least one dimension, providing room to decouple unknowns and linearize the nonlinear inverse problem. Our unique identifiability results subsume all existing literature and cover more general configurations of practical interest. This framework complements classical theories and opens a promising new direction for future development.

math.AP↗

arXiv2026

Emotional intelligence in large language models is fragmented across perception, cognition, and interaction

As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often conflate superficial politeness with deep affective reasoning, failing to distinguish between perceptual accuracy and interactive efficacy. Here, we introduce FACET (Functional Affective Competence and Empathy Test), a psychometrically grounded framework comprising 480 expert-crafted items. Unlike previous metrics, FACET is theoretically anchored in the Mayer-Salovey-Caruso four-branch ability model, operationalizing EI through perception, facilitation, understanding, and management of emotions. Through an evaluation of nine frontier models (including GPT-5, Claude-Sonnet-4), we demonstrate that emotional intelligence is not a monolithic capability but is fragmented across cognitive and interactive dimensions. While frontier models demonstrate robust proficiency in objective emotion recognition and social reasoning, this does not consistently translate to interactive success. We categorize these discrepancies into three distinct performance profiles: cognitive-dominant, interactive-dominant, and context-dependent. These typologies indicate that emotional skills do not scale uniformly with general intelligence or model size; rather, they are shaped by specific alignment paradigms. Notably, we identify hidden emotion recognition as a universal performance bottleneck across all architectures. Our results suggest that current RLHF processes may optimize for "stochastic empathy", a statistical mimicry of emotional syntax, at the expense of integrated affective reasoning. These findings challenge the assumption of linear emotional scaling and provide a rigorous roadmap for developing socially aware agents capable of genuine clinical resonance.

cs.AI↗

arXiv2026

No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool hallucinations, and misaligned actions, which greatly impedes their real-world deployment. To address these challenges, we propose NOD (Navigator-Operator-Director), a heterogeneous multi-agent architecture for service agents. Instead of maintaining task state implicitly in dialogue context as in prior work, we externalize a structured Global State to enable explicit task state tracking and consistent decision-making by the Navigator. Besides, we introduce selective external oversight before critical actions, allowing an independent Director agent to verify execution and intervene when necessary. As such, NOD effectively mitigates error propagation and unsafe behavior in long-horizon tasks. Experiments on $τ^2$-Bench demonstrate that NOD achieves higher task success rates and critical action precision over baselines. More importantly, NOD improves the reliability of service agents by reducing policy violations, tool hallucinations, and user-intent misalignment.

cs.AI↗

arXiv2026

Constraints on Phenomenological Amplitudes of CMB Anisotropy with Multi-Datasets

Cosmic microwave background anisotropies encode crucial information about the early Universe and fundamental cosmological physics. Although the standard $Λ$CDM model provides a successful description of cosmic evolution, persistent cosmological tensions and subtle small-scale anomalies still challenge its internal consistency. In this paper, we investigate six phenomenological amplitude parameters $A_{\rm{new}}$ (new=L, SW, Dop, eISW, lISW, Pol) corresponding to the key effects related to CMB anisotropy: the Lensing, Sachs-Wolfe, Doppler, early Integrated Sachs-Wolfe, late Integrated Sachs-Wolfe, and Polarization effects, respectively. Using modified CAMB and Cobaya packages, we constrain the $Λ$CDM$+A_{\rm{new}}$ models with two data combinations: Planck+DESI+PantheonPlus (PDP) and Planck+ACT+DESI+PantheonPlus (PADP). Only the $Λ$CDM+$A_{\rm{L}}$ is favored by AIC, with $A_{\rm{L}}=1.0656_{-0.0303}^{+0.0304}$ from PDP and $A_{\rm{L}}=1.0795_{-0.0289}^{+0.0260}$ from PADP, which implies 2.16$σ$ and 3.06$σ$ deviation from the $Λ$CDM model; values of $A_{\rm{SW}}$ show 1.21$σ$ and 1.96$σ$ deviations to 1; $A_{\rm{lISW}}$ is poorly constrained because the lISW effect has negligible influence at $\ell \geq 30$; and others are consistent with the $Λ$CDM model. Moreover, no noticeable improvement on the Hubble and $σ_8$ tensions is found within these one-parameter extended scenarios. ACT DR6 high-$\ell$ data strengthens the $Λ$CDM$+A_{\rm{L}}$ preference over the $Λ$CDM model, and reduces $A_{\rm Pol}$ uncertainty by more than one order of magnitude, highlighting the importance of ground-based high-$\ell$ observations for future CMB analyses.

astro-ph.CO↗

arXiv2026

$C^{\infty}$ regularity of the Alt-Phillips Functional for negative powers

In this paper, we study the regularity of the free boundary for minimizers of the Alt-Phillips functional with negative powers \[\mathcal{E}_γ(u)=\int_Ω\frac{1}{2}|\nabla u|^2+\frac{1}γu^{-γ}χ_{\{u>0\}}dx,\quadγ\in(0,2).\] We proved that the free boundaries are $C^{\infty}$ at regular points. A key technical tool is the linearized operator for the PDE satisfied by the partial derivatives of a solution to the Alt-Phillips Euler-Lagrange equation in the negative power case. For this operator we establish a comparison principle, which may have further applications to the Alt-Phillips problem with negative powers.

math.AP↗

arXiv2026

Constraints of dynamical dark energy models from different observational datasets

The measurements of baryon acoustic oscillation by the Dark Energy Spectroscopic Instrument Data Release 2 indicate that dark energy may be dynamical with a time-varying equation of state. This has challenged the core assumptions of the $Λ$CDM model and aroused widespread discussion. Existing work has achieved fruitful results in the dark energy models, exploring various parameterization forms, but it lacks systematic parameter constraints based on the latest dataset combinations. We use $Λ$CDM as a baseline model and carry out rigorous statistical constraints on key cosmological parameters for seven representative parameterization models. The Planck PR4 and DESI DR2 observations are incorporated into our study. We use four datasets: CMB+BAO+PantheonPlus, CMB+BAO+DES-Y5, CMB+BAO+Union3, and CMB+BAO(without LRG1 and LRG2)+DES-Y5. Our results may not effectively alleviate ${H}_{0}$ tension, but may relatively reduce ${σ}_{8}$ tension. By comparing the Akaike Information Criterion and the Bayesian evidence obtained for each model, we demonstrate that the linear Chevallier-Polarski-Linder parameterization is not the optimal choice in all cases. The Logarithmic model shows the best fitting performance among three different SNIa samples. However, with CMB+BAO(without LRG1 and LRG2)+DES-Y5, Jassal-Bagla-Padmanabhan and Chevallier-Polarski-Linder models gain more obvious preference. All two-parameter dynamical dark energy models perform most prominently in the CMB+BAO+DES-Y5 dataset, with the Logarithmic model providing strong evidence to support dynamical dark energy.

astro-ph.CO↗

arXiv2026

Diagnosing CFG Interpretation in LLMs

As LLMs are increasingly integrated into agentic systems, they must adhere to dynamically defined, machine-interpretable interfaces. We evaluate LLMs as in-context interpreters: given a novel context-free grammar, can LLMs generate syntactically valid, behaviorally functional, and semantically faithful outputs? We introduce RoboGrid, a framework that disentangles syntax, behavior, and semantics through controlled stress-tests of recursion depth, expression complexity, and surface styles. Our experiments reveal a consistent hierarchical degradation: LLMs often maintain surface syntax but fail to preserve structural semantics. Despite the partial mitigation provided by CoT reasoning, performance collapses under structural density, specifically deep recursion and high branching, with semantic alignment vanishing at extreme depths. Furthermore, "Alien" lexicons reveal that LLMs rely on semantic bootstrapping from keywords rather than pure symbolic induction. These findings pinpoint critical gaps in hierarchical state-tracking required for reliable, grammar-agnostic agents.

cs.AI↗

arXiv2026

ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge

Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular structures with their properties and reactivities. While large language models (LLMs) have achieved impressive progress, the absence of atomized chemical knowledge results in their superficial understanding of chemistry and limited chemical reasoning capabilities. In this work, to tackle this problem, we develop a Chemical Reasoning LLM, ChemDFM-R. We first construct a comprehensive dataset of atomized chemical knowledge, ChemFG, annotating the presence of functional groups in molecules and the changes of functional groups during chemical reactions, to enhance the model's understanding of the fundamental principles and internal logic of chemistry. Then, we propose a mixed-source distillation method that initializes the model's reasoning capability with limited distilled data, and develop a four-stage training pipeline to equip the model with atomized chemical knowledge and chemical reasoning logic. Experiments on diverse chemical benchmarks demonstrate that ChemDFM-R achieves cutting-edge performance while providing interpretable, rationale-driven outputs, surpassing both the general-domain LLMs and domain-specific chemical LLMs. Moreover, ChemDFM-R achieves comparable or superior performance compared with cutting-edge commercial LLMs, such as o4-mini. Further case studies illustrate how explicit reasoning chains significantly improve the model's reliability, transparency, and practicality in real-world human-AI collaboration scenarios.

cs.CE↗

arXiv2026

Two-Dimensional Superconductivity at the CaZrO3/KTaO3 (001) Heterointerfaces

Two-dimensional superconductivity at KTaO3 (KTO) heterointerfaces has sparked intensive investigations since its discovery, yet whether the (001)-oriented KTO interface hosts superconductivity remains to be elucidated. Here, we provide unambiguous evidence of superconductivity in two-dimensional electron gases (2DEGs) at CaZrO3/KTO(001) heterointerfaces, with a superconducting transition TC up to ~0.25 K. Notably, TC increases linearly with carrier density nS over the range of 4.5*10^13~10.3*10^13 cm^-2. Furthermore, superconductivity exhibits a pronounced dependence on crystallographic orientation, with TC rising from 0.25 K for (001) to 1.04 K for (110) and 2.22 K for (111), underscoring the crucial role of interfacial symmetry in the CaZrO3/KTO system. The two-dimensional nature of the superconducting state is corroborated by the Berezinskii-Kosterlitz-Thouless (BKT) transition and the large anisotropy of the upper critical field. For the CaZrO3/KTO(001) sample with nS=7.7*10^13 cm^-2, the estimated Ginzburg-Landau coherence length ξGL=146.4 nm is larger than the superconducting layer thickness dSC=10.1 nm by a factor of ~14.5, confirming significant two-dimensional confinement of the CaZrO3/KTO(001) superconductor. In addition, we demonstrate that the two-dimensional superconductivity at the CaZrO3/KTO(001) interface can be effectively tuned by applying a back gate voltage. Our findings reveal the existence of two-dimensional superconductivity at CaZrO3/KTO(001), providing a new platform for exploring two-dimensional superconductivity at oxide interfaces.

cond-mat.supr-con↗