Searcharxiv⌕ Search

arXiv subjects

Rui Qi

Publications and source records attributed to Rui Qi.

At least 19 recordsLinked to original sources
arXiv2026

GeoSim: Benchmarking Multi-Field Neural Operators for Geodynamics

Learning reliable surrogates for geodynamic models requires benchmarks that resolve coupled fields and temporal stability. We present GeoSim, a benchmark of high-resolution two-dimensional mantle-plume simulations generated with I2VIS, comprising 237 trajectories across two parameter regimes, with six coupled fields, physical timestamps, and trajectory-level splits. GeoSim defines short-window prediction and autonomous rollout, and evaluates representative neural operators field by field. Across models, we observe a pronounced scalar--velocity gap: scalar fields are reconstructed accurately while velocity errors remain large, and short-window accuracy does not imply stable rollout. We also evaluate MFGNO (Multi-Field Graph Neural Operator), a joint multi-field graph baseline designed for this benchmark; on GeoSim-Plume1, under a fixed per-field objective, it reduces horizontal and vertical velocity errors by 58.4% and 38.5% relative to an independent-field graph baseline, while an explicit field-difference input shows no measurable benefit at this scale. GeoSim provides a reproducible benchmark for field-wise diagnosis and long-horizon evaluation of geodynamic surrogates.

physics.geo-ph↗
arXiv2026

Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning

In multilingual scenarios, queries with equivalent semantics but in different languages could guide the model into different reasoning trajectories, leading to performance disparities. To mitigate this gap, previous studies typically apply a one-size-fits-all query rewriting strategy, such as translation, which overlooks the fact that different scenarios require diverse types of semantic transformations. In this paper, we propose mRewriter-R1, an agentic multilingual query rewriting framework with reinforcement learning. Unlike single-turn rewriting, mRewriter-R1 formulates multilingual query rewriting as a multi-turn sequential decision-making process, where the model dynamically performs multi-aspect optimization through adaptive operator selection. Experimental results demonstrate that mRewriter-R1 outperforms all strong multilingual rewriting baselines on different large reasoning backbones. Further analyses show that the learned policy can adaptively decide on rewriting operators according to query characteristics, exhibiting strong generalization ability across diverse reasoning tasks, and plug-and-play compatibility with heterogeneous reasoning language models.

cs.CL↗
arXiv2026

Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI

Artificial intelligence (AI) has expanded the accessible space for catalyst discovery, yet executing complex screening campaigns still requires constant human intervention to bridge high-level reaction objectives with underlying computational pipelines. Here, we present Autocata, a knowledge-embedded autonomous agent that scales catalytic expertise by encoding multistep reaction pathways into reusable, language-invocable capabilities. Powered by a Transformer pretrained on two million catalyst-adsorbate structures, the system incorporates a capability registry of 79 adsorbate-specialized generative models spanning complex reaction networks across carbon, nitrogen, oxygen, and hydrogen intermediates. Given a high-level natural-language prompt, Autocata deconstructs reaction networks, queries and configures matching generative models, generates candidate surface configurations, enforces physical and geometric validity filtering, and coordinates machine-learning potentials evaluations to rank promising materials. Crucially, the agent adaptively reconfigures workflows when encountering capability boundaries or task bottlenecks. We demonstrate these capabilities across CH4 activation, nitrogen reduction reaction (N2RR), and CO2-to-methanol pathways. By shifting from static toolkits to an adaptive, language-driven computational infrastructure, Autocata lowers the barrier for expert-level catalyst discovery and offers a scalable paradigm for self-driving catalytic research.

physics.chem-ph↗
arXiv2026

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation

Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multilingual collections. However, most existing studies employ a unitive process where queries of equivalent semantics across different languages are processed through a single-turn retrieval and subsequent optimization. Such a ``one-size-fits-all'' strategy is often suboptimal in multilingual settings, as the models occur to knowledge bias and conflict during the interaction with the search engine. To alleviate the issues, we propose LcRL, a multilingual search-augmented reinforcement learning framework that integrates a language-coupled Group Relative Policy Optimization into the policy and reward models. We adopt the language-coupled group sampling in the rollout module to reduce knowledge bias, and regularize an auxiliary anti-consistency penalty in the reward models to mitigate the knowledge conflict. Experimental results demonstrate that LcRL not only achieves competitive performance but is also appropriate for various practical scenarios such as constrained training data and retrieval over collections encompassing a large number of languages. Our code is available at https://github.com/Cherry-qwq/LcRL-Open.

cs.CL↗
arXiv2026

Reaction-Network-Level Discovery of Ammonia Synthesis Catalysts via Ten-Million-Scale Generative Exploration

Catalyst discovery for ammonia synthesis is inherently a reaction-network challenge because catalytic performance is governed not by a single adsorbed intermediate, but by a surface's orchestrated compatibility with multiple distinct intermediates across competing dissociative and associative pathways. However, navigating ultra-large chemical spaces under such multi-intermediate constraints remains a formidable bottleneck for conventional screening workflows. Here, we report a reaction-network-level catalyst discovery framework driven by ten-million-scale generative exploration. By coupling adsorbate-specific generative Transformers with high-throughput machine learning potentials, we systematically map the structure-property landscapes of four critical intermediates (N*, NH*, NNH*, and HNNH*). Scale-dependent overlap analysis shows that the full four-intermediate compatibility space remains strongly under-sampled at conventional 105-106 generative scales, emerging exclusively under ten-million-scale exploration. By generating approximately 15 million configurations per adsorbate, followed by structural compression and machine-learning-potential predictions, we identified 279 highly potential target materials. This sparse compatibility space successfully recovers traditional Fe- and Ru-based motifs while uncovering previously unexplored catalyst families. Representative DFT calculations validate pathway-dependent mechanisms: Fe-V emerges as a dissociative-pathway lead by significantly lowering the initial N2 dissociation barrier, whereas Al-Pd-Zr efficiently stabilizes associative intermediates as an associative-pathway lead. These findings establish multi-intermediate reaction-network compatibility as a robust criterion for discovering advanced catalysts from multi-million generative chemical spaces.

physics.chem-ph↗
arXiv2026

ChatMOSP: A Chemistry-Grounded Mobile Agent for Working-State Catalyst Simulations

Catalytic nanoparticles restructure dynamically under reaction conditions, so their working morphology and activity are governed by temperature, pressure, and gas composition. However, converting experimentally specified environments into physically meaningful morphology-performance simulations remains difficult because the translation of reaction conditions into model-specific energetic, kinetic, and execution parameters requires the specialized knowledge in computational catalysis. Here we report ChatMOSP, a chemistry-grounded mobile scientific agent that translates natural-language and voice-expressed catalytic requests into parameter-validated simulations using the Multi-scale Operando Simulation Package. ChatMOSP maps catalyst identity, temperature, pressure, gas composition, and target observables onto multiscale structure reconstruction and kinetic Monte Carlo tasks, retrieves database parameters or constructs missing inputs from an online literature-retrieval workflow, and executes validated MOSP workflows. Using CO oxidation on Pd nanoparticles as an example, we verify the ChatMOSP simulations capture the temperature-induced transition from faceted to rounded morphologies observed by in-situ TEM experiments either by built-in database or from web-retrieved literature information when the parameters are absent. Moreover, we demonstrate the capability of ChatMOSP to perform end-to-end study at mobile devices to simulate a pressure-coverage-morphology-activity feedback cycle for Pt CO oxidation to interpret the oscillatory CO conversion. These results establish ChatMOSP as a physically constrained mobile agent for accessible and interpretable catalyst working-state simulations.

cond-mat.mtrl-sci↗
arXiv2026

CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation

A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Augmented Generation (RAG). However, the vanilla approach that simply concatenates multiple pieces of knowledge from different languages into the context may fail to improve effectiveness due to the potential disparities across languages. To better leverage multilingual knowledge, we propose CroSearch-R1, a search-augmented reinforcement learning framework to integrate multilingual knowledge into the Group Relative Policy Optimization (GRPO) process. In particular, the approach adopts a multi-turn retrieval strategy with cross-lingual knowledge integration to dynamically align the knowledge from other languages as supplementary evidence into a unified representation space. Furthermore, we introduce a multilingual rollout mechanism to optimize reasoning transferability across languages. Experimental results demonstrate that our framework effectively leverages cross-lingual complementarity and improves the effectiveness of RAG with multilingual collections.

cs.CL↗
arXiv2025

SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models

Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource languages due to resource constraints, which struggles with multilingual reasoning tasks. To this end, we propose Structured-of-Thought (SoT), a training-free method that improves the performance on multilingual reasoning through a multi-step transformation: Language Thinking Transformation and Structured Knowledge Transformation. The SoT method converts language-specific semantic information into language-agnostic structured representations, enabling the models to understand the query in different languages more sophisticated. Besides, SoT effectively guides LLMs toward more concentrated reasoning to maintain consistent underlying reasoning pathways when handling cross-lingual variations in expression. Experimental results demonstrate that SoT outperforms several strong baselines on multiple multilingual reasoning benchmarks when adapting to various backbones of LLMs. It can also be integrated with other training-free strategies for further improvements. Our code is available at https://github.com/Cherry-qwq/SoT.

cs.CL↗
arXiv2024

TransportationGames: Benchmarking Transportation Knowledge of (Multimodal) Large Language Models

Large language models (LLMs) and multimodal large language models (MLLMs) have shown excellent general capabilities, even exhibiting adaptability in many professional domains such as law, economics, transportation, and medicine. Currently, many domain-specific benchmarks have been proposed to verify the performance of (M)LLMs in specific fields. Among various domains, transportation plays a crucial role in modern society as it impacts the economy, the environment, and the quality of life for billions of people. However, it is unclear how much traffic knowledge (M)LLMs possess and whether they can reliably perform transportation-related tasks. To address this gap, we propose TransportationGames, a carefully designed and thorough evaluation benchmark for assessing (M)LLMs in the transportation domain. By comprehensively considering the applications in real-world scenarios and referring to the first three levels in Bloom's Taxonomy, we test the performance of various (M)LLMs in memorizing, understanding, and applying transportation knowledge by the selected tasks. The experimental results show that although some models perform well in some tasks, there is still much room for improvement overall. We hope the release of TransportationGames can serve as a foundation for future research, thereby accelerating the implementation and application of (M)LLMs in the transportation domain.

cs.CL↗
arXiv2023

Stark many-body localization with long-range interactions

In one-dimensional (1D) disorder-free interacting systems, a sufficiently strong linear potential can induce localization of the many-body eigenstates, a phenomenon dubbed as Stark many-body localization (MBL). In this paper, we investigate the fate of Stark MBL in 1D spinless fermions systems with long-range interactions, specifically focusing on the role of interaction strength. We obtain the Stark MBL phase diagrams by computing the mean gap ratio and many-body inverse participation ratio at half-filling. We show that, for short-range interactions, there is a qualitative symmetry between the limits of weak and strong interactions. However, this symmetry is absent in the case of long-range interactions, where the system is always Stark many-body localized at strong interactions, regardless of the linear potential strength. Furthermore, we study the dynamics of imbalance and entanglement with various initial states using time-dependent variational principle (TDVP) numerical methods. We reveal that the dynamical quantities display a strong dependence on the initial conditions, which suggests that the Hilbert-space fragmentation precludes thermalization. Our results demonstrate the robustness of Stark MBL even in the presence of long-range interactions and offer an avenue to explore MBL in disorder-free systems with long-range interactions.

cond-mat.dis-nn↗
arXiv2023

Localization and mobility edges in non-Hermitian disorder-free lattices

The non-Hermitian skin effect (NHSE) is a significant phenomenon observed in non-Hermitian systems under open boundary conditions, where the extensive bulk eigenstates tend to accumulate at the lattice edges. In this article, we investigate how an electric field affects the localization properties in a non-Hermitian mosaic Stark lattice, exploring the interplay between the Stark localization, mobility edge (ME), and the NHSE induced by nonreciprocity. We analytically obtain the Lyapunov exponent and the phase transition points as well as numerically calculate the density distributions and the spectral winding number. We reveal that in the nonreciprocal Stark lattice with the mosaic periodic parameter $κ=1$, there exists a critical electric field strength that describes the transition of the existence-nonexistence of NHSE and is inversely proportional to the lattice size. This transition is consistent with the real-complex transition and topological transition characterized by spectral winding number under periodic boundary conditions. In the strong fields, the Wannier-Stark ladder is recovered, and the Stark localization is sufficient to suppress the NHSE. When the mosaic period $κ=2$, we show that the system manifests an exact non-Hermitian ME and the skin states are still existing in the strong fields, in contrast to the gigantic field can restrain the NHSE in the $κ=1$ case. Moreover, we further study the expansion dynamics of an initially localized state and dynamically probe the existence of the NHSE and the non-Hermitian ME. These results could help us to control the NHSE and the non-Hermitian ME by using electric fields in the disorder-free systems.

cond-mat.dis-nn↗
arXiv2023

Multiple localization transitions and novel quantum phases induced by staggered on-site potential

We propose an one-dimensional generalized Aubry-Andr{é}-Harper (AAH) model with off-diagonal hopping and staggered on-site potential. We find that the localization transitions could be multiple reentrant with the increasing of staggered on-site potential. The multiple localization transitions are verified by the quantum static and dynamic measurements such as the inversed or normalized participation ratios, fractal dimension and survival probability. Based on the finite-size scaling analysis, we also obtain an interesting intermediate phase where the extended, localized and critical states are coexistent in certain regime of model parameters. These results are quite different from those in the generalized AAH model with off-diagonal hopping, and can help us to find novel quantum phases, new localization phenomena in the disordered systems.

cond-mat.dis-nn↗
arXiv2022

Investigations on the flavor-dependent axial charges of the octet baryons

We have investigated the axial charges of the ground octet baryons within the extended chiral constituent quark model, where all the possible compact five-quark Fock components $qqq(q\bar{q}) (q=u, d, s)$ in the baryons are considered. The transition couplings between the three- and five-quark components in the baryons are assumed to be via the $^{3}P_{0}$ mechanism, which could reproduce the sea asymmetry in proton very well. The numerical results for the flavor-dependent axial charges of the octet baryons are comparable to those predicted by other theoretical approaches. It is shown that the singlet axial charges of the octet baryons, which should indicate total baryons spin arising from the spin of the quarks, fall in the range $0.45-0.75$ in present model. This is in consistent with the predictions by lattice QCD and chiral perturbation theory. It's also very interesting that the light quarks spin $Δu$ and $Δd$ in the $Λ$ baryon are of small but negative values, which exactly vanish in the traditional three-quark model.

hep-ph↗
arXiv2022

Non-neglectable entropy effect on sintering of supported nanoparticles

Sintering refers to particle coalescence by heat, which has been known as a thermal phenomenon involving all aspects of natural science for centuries. It is particularly important in heterogeneous catalysis because normally sintering results in deactivation of the catalysts. In previous studies, the enthalpy contribution was considered to be dominant in sintering and the entropy effect is generally considered neglectable. However, we unambiguously demonstrate in this work that entropy could prevail over the enthalpy contribution to dominate the sintering behavior of supported nanoparticles (NPs) by designed experiments and improved theoretical framework. Using in situ Cs-corrected environmental scanning transmission electron microscopy and synchrotron-based ambient pressure X-ray photoelectron spectroscopy, we observe the unprecedent entropy-driven phenomenon that supported NPs reversibly redisperse upon heating and sinter upon cooling in three systems (Pd-CeO2, Cu-TiO2, Ag-TiO2). We quantitatively show that the configurational entropy of highly dispersed ad-atoms is large enough to reverse their sintering tendency at the elevated temperature. This work reshapes the basic understanding of sintering at the nanoscale and opens the door for various de-novo designs of thermodynamically stable nanocatalysts.

cond-mat.mtrl-sci↗
arXiv2018

Realization of a scalable Laguerre-Gaussian mode sorter based on a robust radial mode sorter

The transverse structure of light is recognized as a resource that can be used to encode information onto photons and has been shown to be useful to enhance communication capacity as well as resolve point sources in superresolution imaging. The Laguerre-Gaussian (LG) modes form a complete and orthonormal basis set and are described by a radial index p and an orbital angular momentum (OAM) index l. Earlier works have shown how to build a sorter for the radial index p or/and the OAM index l of LG modes, but a scalable and dedicated LG mode sorter which simultaneous determinate p and l is immature. Here we propose and experimentally demonstrate a scheme to accomplish complete LG mode sorting, which consists of a novel, robust radial mode sorter that can be used to couple radial modes to polarizations, an l-dependent phase shifter and an OAM mode sorter. Our scheme is in principle efficient, scalable, and crosstalk-free, and therefore has potential for applications in optical communications, quantum information technology, superresolution imaging, and fiber optics.

physics.optics↗
arXiv2002

Collapse helps to probe the structure of particles

We present a possible method to probe the inner structure of particles based on one kind of promising dynamical collapse theory. It is shown that the present decay data of KL meson indicates that quarks have no inner structure.

quant-ph↗
arXiv2002

Space-time transformation for superluminal signaling

We analyze the possible implication of the existence of superluminal signaling for space-time structure. A new space-time transformation for superluminal signaling is presented based on the superluminal synchrony method. We argue that Lorentz transformation should be replaced by the new transformation in case of the existence of superluminal signaling. Furthermore, we discuss the possible existence of absolute frame, and give a possible practical method to probe it.

quant-ph↗