Searcharxiv⌕ Search

arXiv subjects

Xing Fan

Publications and source records attributed to Xing Fan.

At least 37 records · Page 2Linked to original sources

Memetic Search for Green Vehicle Routing Problem with Private Capacitated Refueling Stations

The green vehicle routing problem with private capacitated alternative fuel stations (GrVRP-PCAFS) extends the traditional green vehicle routing problem by considering capacitated refueling stations, where a limited number of vehicles can refuel simultaneously and additional vehicles must wait. This feature presents new challenges for route planning, as waiting times at stations must be managed while keeping route durations within limits and reducing total travel distance. This article presents METS, a novel memetic algorithm (MA) with separate constraint-based tour segmentation (SCTS) and a local search procedure tailored for solving GrVRP-PCAFS. METS balances exploration and exploitation through three key components. For exploration, the SCTS strategy splits giant tours to generate diverse solutions, and the search process is guided by a comprehensive fitness evaluation function to dynamically control feasibility and diversity to produce solutions that are both diverse and near-feasible. For exploitation, the local search procedure incorporates tailored move operators with constant-time evaluation mechanisms, enabling efficient examination of large solution neighborhoods. Experimental results demonstrate that METS discovers 31 new best-known solutions out of 40 instances in existing benchmark sets, achieving substantial improvements over current state-of-the-art methods. Additionally, a new large-scale benchmark set based on real-world logistics data is introduced to facilitate future research.

cs.NE↗

ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code

Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing mechanisms, but they are typically heuristic and task-specific, lacking a general framework for adaptive reasoning. In this paper, we present ARM2, a unified model that adaptively balances reasoning performance and efficiency across multiple formats through a reinforcement learning framework augmented with length-aware optimization. Beyond conventional natural language inference, ARM2 integrates vision understanding, extending its applicability to multimodal. Moreover, ARM2 integrates executable code into reasoning, enabling substantial reductions in token cost while preserving task performance compared to long CoT. Experiments demonstrate that ARM2 achieves performance on par with traditional reasoning models trained with GRPO, while reducing token usage by over 70% on average. We further conduct extensive analyses to validate the effectiveness of ARM2 and the soundness of its design.

cs.CL↗

Analyzing and Internalizing Complex Policy Documents for LLM Agents

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internalization harder. We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels, enabling systematic evaluation of agents' ability to handle complexity and offering a unified framework for assessing policy internalization. Our analysis shows that complex policy specifications governing workflows pose major reasoning challenges. Supporting internalization with gold user agent interaction trajectories containing chain-of-thought (CoT) annotations via supervised fine-tuning (SFT) is data-intensive and degrades sharply as policy complexity increases. To mitigate data and reasoning burdens, we propose Category-Aware Policy Continued Pretraining (CAP-CPT). Our automated pipeline parses policy documents to extract key specifications, grouping them into factual, behavioral, and conditional categories, and isolating complex conditions that drive workflow complexity. This guides targeted data synthesis and enables agents to internalize policy information through an autoregressive pretraining loss. Experiments show CAP-CPT improves SFT baselines in all settings, with up to 41% and 22% gains on Qwen-3-32B, achieving 97.3% prompt length reduction on CC-Gen and further enhancing tau-Bench with minimal SFT data.

cs.AI↗

One-Electron Quantum Cyclotron as a Milli-eV Dark-Photon Detector

We propose using trapped electrons as high-$Q$ resonators for detecting meV dark photon dark matter. When the rest energy of the dark photon matches the energy splitting of the two lowest cyclotron levels, the first excited state of the electron cyclotron will be resonantly excited. A proof-of-principle measurement, carried out with one electron, demonstrates that the method is background-free over a 7.4 day search. It sets a limit on dark photon dark matter at 148 GHz (0.6 meV) that is around 75 times better than previous constraints. Dark photon dark matter in the 0.1-1 meV mass range (20-200 GHz) could likely be detected at a similar sensitivity in an apparatus designed for dark photon detection.

hep-ex↗

WINELL: Wikipedia Never-Ending Updating with LLM Agents

Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by the vision of continuous knowledge acquisition in NELL and fueled by advances in LLM-based agents, this paper introduces WiNELL, an agentic framework for continuously updating Wikipedia articles. Our approach employs a multi-agent framework to aggregate online information, select new and important knowledge for a target entity in Wikipedia, and then generate precise edit suggestions for human review. Our fine-grained editing models, trained on Wikipedia's extensive history of human edits, enable incorporating updates in a manner consistent with human editing behavior. Our editor models outperform both open-source instruction-following baselines and closed-source LLMs (e.g., GPT-4o) in key information coverage and editing efficiency. End-to-end evaluation on high-activity Wikipedia pages demonstrates WiNELL's ability to identify and suggest timely factual updates. This opens up a promising research direction in LLM agents for automatically updating knowledge bases in a never-ending fashion.

cs.CL↗

Nuclear Electric Quadrupole Moment-Induced Parity Doubling in Molecules for Symmetry-Violation Searches

Searches for the nuclear magnetic quadrupole moment (MQM) and nuclear Schiff moment (NSM) have high discovery potential for violations of time ($T$) and parity ($P$) reversal symmetries beyond the Standard Model. Molecules containing heavy nuclei are typically used to enhance the sensitivity to MQMs and NSMs due to their strong internal electric fields and potential octupole deformation. To extract these effects in the laboratory frame, a bias electric field is required to polarize the molecule by mixing states of opposite parity (parity doublets). Typical heavy nuclei that are sensitive to symmetry-violation also possess large nuclear electric quadrupole moments (EQMs) when its nuclear spin is $I\geq1$. We show that EQMs can significantly modify the energy splitting between parity doublet states and thus change the required polarizing electric field. As a result, the EQM-induced energy splitting must be taken into account in designing such experiments. We provide qualitative estimates of parity doubling from EQMs and supporting \textit{ab initio} calculations, along with implications for candidate molecules in symmetry-violation searches.

physics.atom-ph↗

Quantum Logic Spectroscopy of an Electron and Positron for Precise Tests of the Standard Model

We propose a scheme for quantum logic spectroscopy of an electron or positron in a Penning trap. An electron or positron in a spectroscopy trap is coupled to a remote logic electron or positron via a wire to achieve motional entanglement. By separating the two traps, one can significantly improve magnetic field homogeneity, microwave characteristics, and detection sensitivity. The proposed scheme will improve the measurement precision of the electron's and positron's magnetic moments and charge-to-mass ratios, enabling precise tests of the Standard Model of particle physics.

quant-ph↗

Knowledge Enhanced Multi-Domain Recommendations in an AI Assistant Application

This work explores unifying knowledge enhanced recommendation with multi-domain recommendation systems in a conversational AI assistant application. Multi-domain recommendation leverages users' interactions in previous domains to improve recommendations in a new one. Knowledge graph enhancement seeks to use external knowledge graphs to improve recommendations within a single domain. Both research threads incorporate related information to improve the recommendation task. We propose to unify these approaches: using information from interactions in other domains as well as external knowledge graphs to make predictions in a new domain that would not be possible with either information source alone. We develop a new model and demonstrate the additive benefit of these approaches on a dataset derived from millions of users' queries for content across three domains (videos, music, and books) in a live virtual assistant application. We demonstrate significant improvement on overall recommendations as well as on recommendations for new users of a domain.

cs.IR↗

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such as jailbreak attacks, which attempt to induce harmful content. Researching attack methods allows us to better understand the limitations of LLM and make trade-offs between helpfulness and safety. However, existing jailbreak attacks are primarily based on opaque optimization techniques (e.g. token-level gradient descent) and heuristic search methods like LLM refinement, which fall short in terms of transparency, transferability, and computational cost. In light of these limitations, we draw inspiration from the evolution and infection processes of biological viruses and propose LLM-Virus, a jailbreak attack method based on evolutionary algorithm, termed evolutionary jailbreak. LLM-Virus treats jailbreak attacks as both an evolutionary and transfer learning problem, utilizing LLMs as heuristic evolutionary operators to ensure high attack efficiency, transferability, and low time cost. Our experimental results on multiple safety benchmarks show that LLM-Virus achieves competitive or even superior performance compared to existing attack methods.

cs.CR↗

High-temperature Phonon Coherence and Tunneling Effect in Semiconductor Superlattices

Phonons, the quanta of lattice vibrations, are primary heat carriers for semiconductors and dielectrics. The demand of effective phonon manipulation urgently emerges, because the thermal management is crucial for the ongoing development of micro/nano semiconductor devices towards higher integration and power densities1, 2. Phonons also show wave-particle duality, while they are commonly treated as particle flows in current semiconductor structures3, 4. However, it sees constraints when the structure size reduces to nano and atomic scales, where the wave behavior of phonons begins to dominate, and studies of these phonon behaviors and their manipulations become long-standing challenges in experiments5. Here we show the experimental realization of coherent phonon transport, a wave-based thermal conduction fashion, in semiconductor structures. We report the successful observation of robust phonon coherence and tunneling effect in InAs/AlAs superlattices over an extensive temperature range up to 500 K, a breakthrough towards practical-application temperature for semiconductors compared with cryogenic conditions6. Our results demonstrate that the phonon coherence is robust even at a record-high interface density due to the dominating long-wavelength phonons, and the first-principles calculations clearly reveal their wave-particle duality. This revelation heralds a promising pathway towards efficient thermal phonon engineering at extreme scales, holding implications for a broad spectrum of semiconductor device applications, including microelectronics, optoelectronics, and thermoelectrics.

cond-mat.mtrl-sci↗

Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction

Motion prediction plays an essential role in autonomous driving systems, enabling autonomous vehicles to achieve more accurate local-path planning and driving decisions based on predictions of the surrounding vehicles. However, existing methods neglect the potential missing values caused by object occlusion, perception failures, etc., which inevitably degrades the trajectory prediction performance in real traffic scenarios. To address this limitation, we propose a novel end-to-end framework for incomplete vehicle trajectory prediction, named Multi-scale Temporal Fusion Transformer (MTFT), which consists of the Multi-scale Attention Head (MAH) and the Continuity Representation-guided Multi-scale Fusion (CRMF) module. Specifically, the MAH leverages the multi-head attention mechanism to parallelly capture multi-scale motion representation of trajectory from different temporal granularities, thus mitigating the adverse effect of missing values on prediction. Furthermore, the multi-scale motion representation is input into the CRMF module for multi-scale fusion to obtain the robust temporal feature of the vehicle. During the fusion process, the continuity representation of vehicle motion is first extracted across time steps to guide the fusion, ensuring that the resulting temporal feature incorporates both detailed information and the overall trend of vehicle motion, which facilitates the accurate decoding of future trajectory that is consistent with the vehicle's motion trend. We evaluate the proposed model on four datasets derived from highway and urban traffic scenarios. The experimental results demonstrate its superior performance in the incomplete vehicle trajectory prediction task compared with state-of-the-art models, e.g., a comprehensive performance improvement of more than 39% on the HighD dataset.

cs.CV↗

Bringing Generative AI to Adaptive Learning in Education

The recent surge in generative AI technologies, such as large language models and diffusion models, has boosted the development of AI applications in various domains, including science, finance, and education. Concurrently, adaptive learning, a concept that has gained substantial interest in the educational sphere, has proven its efficacy in enhancing students' learning efficiency. In this position paper, we aim to shed light on the intersectional studies of these two methods, which combine generative AI with adaptive learning concepts. By presenting discussions about the benefits, challenges, and potentials in this field, we argue that this union will contribute significantly to the development of the next-stage learning format in education.

cs.CY↗

Foundation Models for Education: Promises and Prospects

With the advent of foundation models like ChatGPT, educators are excited about the transformative role that AI might play in propelling the next education revolution. The developing speed and the profound impact of foundation models in various industries force us to think deeply about the changes they will make to education, a domain that is critically important for the future of humans. In this paper, we discuss the strengths of foundation models, such as personalized learning, education inequality, and reasoning capabilities, as well as the development of agent architecture tailored for education, which integrates AI agents with pedagogical frameworks to create adaptive learning environments. Furthermore, we highlight the risks and opportunities of AI overreliance and creativity. Lastly, we envision a future where foundation models in education harmonize human and AI capabilities, fostering a dynamic, inclusive, and adaptive educational ecosystem.

cs.CY↗

RecMind: Large Language Model Powered Agent For Recommendation

While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints. Thus, we designed an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge, utilizing tools with careful planning to provide zero-shot personalized recommendations. We propose a Self-Inspiring algorithm to improve the planning ability. At each intermediate step, the LLM self-inspires to consider all previously explored states to plan for the next step. This mechanism greatly improves the model's ability to comprehend and utilize historical information in planning for recommendation. We evaluate RecMind's performance in various recommendation scenarios. Our experiment shows that RecMind outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.

cs.IR↗

Metastable Charge Distribution Between Degenerate Landau Levels

We study two dimensional electron systems confined in wide quantum wells whose subband separation is comparable with the Zeeman energy. Two N = 0 Landau levels from different subbands and with opposite spins are pinned in energy when they cross each other and electrons can freely transfer between them. When the disorder is strong, we observe clear hysteresis in our data corresponding to instability of the electron distribution in the two crossing levels. When the intra-layer interaction dominates, multiple minima appear when a Landau level is 1/3 or 2/3 filled and fractional quantum hall effect can be stabilized.

cond-mat.mes-hall↗

New bounds and future prospects for axion force searches at Penning trap experiments

In this note we consider Penning trap experiments as probes of axion-mediated forces. We show that the current measurement of electron's $g$-factor already sets a new exclusion limit for monopole-dipole axion forces acting on the electron spin. We also show that the Penning trap's capability of switching an electron and a positron can isolate the effect of an axion force and suppress systematic effects.

hep-ph↗

Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding

Conversational AI systems such as Alexa need to understand defective queries to ensure robust conversational understanding and reduce user friction. These defective queries often arise from user ambiguities, mistakes, or errors in automatic speech recognition (ASR) and natural language understanding (NLU). Personalized query rewriting is an approach that focuses on reducing defects in queries by taking into account the user's individual behavior and preferences. It typically relies on an index of past successful user interactions with the conversational AI. However, unseen interactions within the user's history present additional challenges for personalized query rewriting. This paper presents our "Collaborative Query Rewriting" approach, which specifically addresses the task of rewriting new user interactions that have not been previously observed in the user's history. This approach builds a "User Feedback Interaction Graph" (FIG) of historical user-entity interactions and leverages multi-hop graph traversal to enrich each user's index to cover future unseen defective queries. The enriched user index is called a Collaborative User Index and contains hundreds of additional entries. To counteract precision degradation from the enlarged index, we add additional transformer layers to the L1 retrieval model and incorporate graph-based and guardrail features into the L2 ranking model. Since the user index can be pre-computed, we further investigate the utilization of a Large Language Model (LLM) to enhance the FIG for user-entity link prediction in the Video/Music domains. Specifically, this paper investigates the Dolly-V2 7B model. We found that the user index augmented by the fine-tuned Dolly-V2 generation significantly enhanced the coverage of future unseen user interactions, thereby boosting QR performance on unseen queries compared with the graph traversal only approach.

cs.AI↗

KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting

Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions. When there is an entity error, it imposes extra challenges for a dialogue system to produce satisfactory responses. In this work, we propose KG-ECO: Knowledge Graph enhanced Entity COrrection for query rewriting, an entity correction system with corrupt entity span detection and entity retrieval/re-ranking functionalities. To boost the model performance, we incorporate Knowledge Graph (KG) to provide entity structural information (neighboring entities encoded by graph neural networks) and textual information (KG entity descriptions encoded by RoBERTa). Experimental results show that our approach yields a clear performance gain over two baselines: utterance level QR and entity correction without utilizing KG information. The proposed system is particularly effective for few-shot learning cases where target entities are rarely seen in training or there is a KG relation between the target entity and other contextual entities in the query.

cs.CL↗