arXiv subjects

Kun Luo

Publications and source records attributed to Kun Luo.

At least 19 recordsLinked to original sources

arXiv2026

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do more than simply search longer: it should recursively improve its current answer by verifying intermediate results and using the partially verified state to guide subsequent refinement. We introduce AREX, a family of Recursively Self-Improving (RSI) deep research agents. AREX alternates between an inner research loop that gathers evidence and constructs a provisional answer, and an outer self-improvement loop that audits the answer constraint-wise, identifies unresolved claims, and launches targeted follow-up research. To sustain RSI over long horizons, AREX learns an autonomous context-update tool that compresses growing interaction history into a compact improvement state preserving verified evidence and unresolved constraints, without relying on an external model. We train AREX on verified synthetic tasks and high-quality trajectories through agentic mid-training and long-horizon reinforcement learning. To mitigate sparse final rewards during long horizon learning, we emphasize key steps where decisive evidence is acquired or erroneous research directions are corrected. We instantiate a dense 4B model and a 122B-A10B Mixture-of-Experts model. Across BrowseComp, WideSearch, DeepSearchQA, Humanity's Last Exam (HLE), and other reasoning and tool-use benchmarks, AREX substantially outperforms comparable-scale baselines and remains competitive with models using substantially more activated parameters.

cs.AI↗

arXiv2026

Suppression of Non-Hermitian Skin Effect by Pseudomagnetic Field in Honeycomb Lattice

Magnetic suppression of the non-Hermitian skin effect (NHSE) offers a viable route for its control. While the NHSE has been realized in various classical-wave platforms, only pseudomagnetic fields (PMFs), which preserve time-reversal symmetry, can be engineered in such systems; however, their interplay with the NHSE remains underexplored. Here, we investigate this interplay in a non-Hermitian honeycomb lattice by considering two distinct mechanisms for generating PMFs: monotonically increasing strain and spatially modulated gain and loss. We show that in both scenarios, PMFs can efficiently suppress the NHSE by driving skin modes into the bulk, accompanied by a reduction of the skin topological area and a contraction of the complex-energy spectrum under periodic boundary conditions. This mechanism is insensitive to boundary details and holds for various edge terminations, including zigzag, bearded, armchair, and twig edges. Our results establish PMFs as a versatile and effective means to control the NHSE, and point toward feasible implementations in a broad range of artificial platforms, including photonic and acoustic metamaterials as well as topolectrical circuits.

cond-mat.other↗

arXiv2026

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents' capability in driving this process, we present AutoResearchBench, a dedicated benchmark for autonomous scientific literature discovery. AutoResearchBench consists of two complementary task types: (1) Deep Research, which requires tracking down a specific target paper through a progressive, multi-step probing process, and (2) Wide Research, which requires comprehensively collecting a set of papers satisfying given conditions. Compared to previous benchmarks on agentic web browsing, AutoResearchBench is distinguished along three dimensions: it is research-oriented, calling for in-depth comprehension of scientific concepts; literature-focused, demanding fine-grained utilization of detailed information; and open-ended, involving an unknown number of qualified papers and thus requiring deliberate reasoning and search throughout. These properties make AutoResearchBench uniquely suited for evaluating autonomous research capabilities, and extraordinarily challenging. Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research, while many other strong baselines fall below 5%. We publicly release the dataset and evaluation pipeline to facilitate future research in this direction. We publicly release the dataset, evaluation pipeline, and code at https://github.com/CherYou/AutoResearchBench.

cs.AI↗

arXiv2026

LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs

Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging when using lightweight vision-language models (VLMs), whose limited reasoning capacity makes long-horizon navigation unreliable. In this paper, we propose LightZeroNav to tackle the three major bottlenecks when using lightweight VLMs in zero-shot VLN-CE,i.e.,information redundancy from multi-source inputs, inaccurate progress estimation caused by noisy textual memory, and task entanglement between action execution and stage transition. Using only RGB observations and a lightweight open-source Qwen3-VL-8B backbone, LightZeroNav achieves competitive performance with GPT-4o (~200B) without task-specific training, graph search, or waypoint predictors, demonstrating its effectiveness in zero-shot VLN-CE.

cs.CV↗

arXiv2026

DeepXiv-SDK: An Agentic Data Interface for Scientific Literature

LLM-agents are increasingly used to accelerate the progress of scientific research. Yet a persistent bottleneck is data access: agents not only lack readily available tools for retrieval, but also have to work with unstrcutured, human-centric data on the Internet, such as HTML web-pages and PDF files, leading to excessive token consumption, limit working efficiency, and brittle evidence look-up. This gap motivates the development of \textit{an agentic data interface}, which is designed to enable agents to access and utilize scientific literature in a more effective, efficient, and cost-aware manner. In this paper, we introduce DeepXiv-SDK, which offers a three-layer agentic data interface for scientific literature. 1) Data Layer, which transforms unstructured, human-centric data into normalized and structured representations in JSON format, improving data usability and enabling progressive accessibility of the data. 2) Service Layer, which presents readily available tools for data access and ad-hoc retrieval. It also enables a rich form of agent usage, including CLI, MCP, and Python SDK. 3) Application Layer, which creates a built-in agent, packaging basic tools from the service layer to support complex data access demands. DeepXiv-SDK currently supports the complete ArXiv corpus, and is synchronized daily to incorporate new releases. It is designed to extend to all common open-access corpora, such as PubMed Central, bioRxiv, medRxiv, and chemRxiv. We release RESTful APIs, an open-source Python SDK, and a web demo showcasing deep search and deep research workflows. DeepXiv-SDK is free to use with registration.

cs.DL↗

arXiv2025

InfoFlow: Reinforcing Search Agent Via Reward Density Optimization

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep search scenarios, where agents expend significant exploratory costs for infrequent and often null final rewards. In this paper, we formalize this challenge as the \textbf{Reward Density Optimization} problem, which aims to improve the reward obtained per unit of exploration cost. This paper introduce \textbf{InfoFlow}, a systematic framework that tackles this problem from three aspects. 1) \textbf{Subproblem decomposition}: breaking down long-range tasks to assign process rewards, thereby providing denser learning signals. 2) \textbf{Failure-guided hints}: injecting corrective guidance into stalled trajectories to increase the probability of successful outcomes. 3) \textbf{Dual-agent refinement}: employing a dual-agent architecture to offload the cognitive burden of deep exploration. A refiner agent synthesizes the search history, which effectively compresses the researcher's perceived trajectory, thereby reducing exploration cost and increasing the overall reward density. We evaluate InfoFlow on multiple agentic search benchmarks, where it significantly outperforms strong baselines, enabling lightweight LLMs to achieve performance comparable to advanced proprietary LLMs.

cs.CL↗

arXiv2025

CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage

Security Operations Centers (SOCs) are overwhelmed by tens of thousands of daily alerts, with only a small fraction corresponding to genuine attacks. This overload creates alert fatigue, leading to overlooked threats and analyst burnout. Classical detection pipelines are brittle and context-poor, while recent LLM-based approaches typically rely on a single model to interpret logs, retrieve context, and adjudicate alerts end-to-end -- an approach that struggles with noisy enterprise data and offers limited transparency. We propose CORTEX, a multi-agent LLM architecture for high-stakes alert triage in which specialized agents collaborate over real evidence: a behavior-analysis agent inspects activity sequences, evidence-gathering agents query external systems, and a reasoning agent synthesizes findings into an auditable decision. To support training and evaluation, we release a dataset of fine-grained SOC investigations from production environments, capturing step-by-step analyst actions and linked tool outputs. Across diverse enterprise scenarios, CORTEX substantially reduces false positives and improves investigation quality over state-of-the-art single-agent LLMs.

cs.CL↗

arXiv2025

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning

Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation of semantic prompts is too coarse-grained to capture fine-grained relationships; (2) these methods lack explicit modeling of image objects and their semantic relationships. To address these limitations, we propose RACap, a relation-aware retrieval-augmented model for image captioning, which not only mines structured relation semantics from retrieval captions, but also identifies heterogeneous objects from the image. RACap effectively retrieves structured relation features that contain heterogeneous visual information to enhance the semantic consistency and relational expressiveness. Experimental results show that RACap, with only 10.8M trainable parameters, achieves superior performance compared to previous lightweight captioning models.

cs.CV↗

arXiv2025

Open Data Synthesis For Deep Research

Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordinating multi-step reasoning, and synthesizing evidence from diverse sources. We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems (HCSPs), which are fundamentally different from single-constraint, multi-hop, or flat CSP formulations. However, existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity, while recent synthetic datasets often introduce shortcut reasoning, knowledge leakage, or lack sufficient structural depth. To address this gap, we introduce InfoSeek, a scalable framework for synthesizing complex Deep Research tasks. InfoSeek uses a dual-agent system to recursively build a Research Tree from large-scale webpages, blurring intermediate nodes into valid sub-problems, and converting these trees into natural language questions that require traversing the full hierarchy. It also enables rapid scaling, yielding over 50K training examples, a curated test set, and reasoning trajectories generated via reject sampling. Experiments show that models trained on InfoSeek consistently outperform strong baselines. On a challenging benchmark BrowseComp-Plus, 3B LLMs optimized with InfoSeek surpass much larger 32B models and lightweight commercial APIs (e.g., Gemini2.5-Flash), while achieving performance comparable to stronger APIs (e.g., Gemini2.5-Pro). By preserving meta-information such as intermediate steps and retrieval labels, InfoSeek further supports advanced optimization strategies, including compound reward design and trajectory-level exploration. We provide our codes and datasets in \href{https://github.com/VectorSpaceLab/InfoSeek}{this repository}.

cs.CL↗

arXiv2025

Fabry-Perot interference in three dimensional second-order topological insulator constrictions

The gapless chiral hinge states of three dimensional second-order topological insulators (SOTIs) support a quantized conductance plateau on thick nanowire. Here, we numerical study the conductance of SOTI constrictions. According to finite size effects, the hinge states in narrow region could be hybridized, which will induce reflection at the two ends of constrictions. The conductance exists the Fabry-Perot oscillation pattern because of multiple reflections. We also study the impact of the magnetic field on the Fabry-Perot interference. We show the dimensional effect that the magnetic field leads to the electrons being localized on two hinges. Our results are robust against moderate disorder so that we expect these Fabry-Perot patterns could be observed in experiments.

cond-mat.mes-hall↗

arXiv2025

OmniGen2: Towards Instruction-Aligned Multimodal Generation

In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2

cs.CV↗

arXiv2025

Direct evidence and atomic-scale mechanisms of reduced dislocation mobility in an inorganic semiconductor under illumination

Photo-plasticity in semiconductors, wherein their mechanical properties such as strength, hardness and ductility are influenced by light exposure, has been reported for several decades. Although such phenomena have drawn significant attention for the manufacturability and usage of deformable semiconductor devices, their underlying mechanisms are not well understood due to the lack of direct evidence. Here we provide experimental observation and atomic insights into the reduced mobility of dislocations in zinc sulfide, as a model material, under light. Using photo-nanoindentation and transmission electron microscopy, we observe that dislocations glide shorter distances under light than those in darkness and there are no apparent deformation twins in both conditions. By atomic-scale simulations, we demonstrate that the decreased dislocation mobility is attributed to the increased Peierls stress for dislocation motion and enhanced stress fields around dislocation cores due to photoexcitation. This study improves the understanding of photo-plastic effects in inorganic semiconductors, offering the opportunities for modulating their mechanical properties using light.

cond-mat.mtrl-sci↗

arXiv2025

PT-PINNs: A Parametric Engineering Turbulence Solver based on Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) demonstrate promising potential in parameterized engineering turbulence optimization problems but face challenges, such as high data requirements and low computational accuracy when applied to engineering turbulence problems. This study proposes a framework that enhances the ability of PINNs to solve parametric turbulence problems without training datasets from experiments or CFD-Parametric Turbulence PINNs (PT-PINNs)). Two key methods are introduced to improve the accuracy and robustness of this framework. The first is a soft constraint method for turbulent viscosity calculation. The second is a pre-training method based on the conservation of flow rate in the flow field. The effectiveness of PT-PINNs is validated using a three-dimensional backward-facing step (BFS) turbulence problem with two varying parameters (Re = 3000-200000, ER = 1.1-1.5). PT-PINNs produce predictions that closely match experimental data and computational fluid dynamics (CFD) results across various conditions. Moreover, PT-PINNs offer a computational efficiency advantage over traditional CFD methods. The total time required to construct the parametric BFS turbulence model is 39 hours, one-sixteenth of the time required by traditional numerical methods. The inference time for a single-condition prediction is just 40 seconds-only 0.5% of a single CFD computation. These findings highlight the potential of PT-PINNs for future applications in engineering turbulence optimization problems.

physics.flu-dyn↗

arXiv2025

Does RAG Really Perform Bad For Long-Context Processing?

The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strategy for this problem, as it enables LLMs to make selective use of the long context for efficient computation. However, existing RAG approaches lag behind other long-context processing methods due to inherent limitations on inaccurate retrieval and fragmented contexts. To address these challenges, we introduce RetroLM, a novel RAG framework for long-context processing. Unlike traditional methods, RetroLM employs KV-level retrieval augmentation, where it partitions the LLM's KV cache into contiguous pages and retrieves the most crucial ones for efficient computation. This approach enhances robustness to retrieval inaccuracy, facilitates effective utilization of fragmented contexts, and saves the cost from repeated computation. Building on this framework, we further develop a specialized retriever for precise retrieval of critical pages and conduct unsupervised post-training to optimize the model's ability to leverage retrieved information. We conduct comprehensive evaluations with a variety of benchmarks, including LongBench, InfiniteBench, and RULER, where RetroLM significantly outperforms existing long-context LLMs and efficient long-context processing methods, particularly in tasks requiring intensive reasoning or extremely long-context comprehension.

cs.CL↗

arXiv2024

Making Text Embedders Few-Shot Learners

Large language models (LLMs) with decoder-only architectures demonstrate remarkable in-context learning (ICL) capabilities. This feature enables them to effectively handle both familiar and novel tasks by utilizing examples provided within their input context. Recognizing the potential of this capability, we propose leveraging the ICL feature in LLMs to enhance the process of text embedding generation. To this end, we introduce a novel model bge-en-icl, which employs few-shot examples to produce high-quality text embeddings. Our approach integrates task-related examples directly into the query side, resulting in significant improvements across various tasks. Additionally, we have investigated how to effectively utilize LLMs as embedding models, including various attention mechanisms, pooling methods, etc. Our findings suggest that retaining the original framework often yields the best results, underscoring that simplicity is best. Experimental results on the MTEB and AIR-Bench benchmarks demonstrate that our approach sets new state-of-the-art (SOTA) performance. Our model, code and dataset are freely available at https://github.com/FlagOpen/FlagEmbedding .

cs.IR↗

arXiv2024

Dispersive wave propagation in disordered flexible fibers enhances stress attenuation

We experimentally and computationally analyze impact-shock-induced stress wave propagation in packings of disordered flexible fibers. We find that dispersive wave propagation, associated with large stress attenuation, occurs much more prevalently in systems with larger fiber aspect ratios and moderate fiber flexibility. We trace these features to the microstructural properties of fiber contact chains and the energy-trapping abilities of deformable fibers. These findings provide new insights into physics of the shock-impacted flexible fiber packings and open the way towards an improved granular-material-based damping technology.

cond-mat.soft↗

arXiv2024

Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research has explored using large language models (LLMs) as retrievers, achieving SOTA performance across various tasks. Despite these advancements, the specific benefits of LLMs over traditional retrievers and the impact of different LLM configurations, such as parameter sizes, pretraining duration, and alignment processes on retrieval tasks remain unclear. In this work, we conduct a comprehensive empirical study on a wide range of retrieval tasks, including in domain accuracy, data efficiency, zero shot generalization, lengthy retrieval, instruction based retrieval, and multi task learning. We evaluate over 15 different backbone LLMs and non LLMs. Our findings reveal that larger models and extensive pretraining consistently enhance in domain accuracy and data efficiency. Additionally, larger models demonstrate significant potential in zero shot generalization, lengthy retrieval, instruction based retrieval, and multi task learning. These results underscore the advantages of LLMs as versatile and effective backbone encoders in dense retrieval, providing valuable insights for future research and development in this field.

cs.CL↗

arXiv2024

Enhanced Cascade Prostate Cancer Classifier in mp-MRI Utilizing Recall Feedback Adaptive Loss and Prior Knowledge-Based Feature Extraction

Prostate cancer is the second most common cancer in males worldwide, and mpMRI is commonly used for diagnosis. However, interpreting mpMRI is challenging and requires expertise from radiologists. This highlights the urgent need for automated grading in mpMRI. Existing studies lack integration of clinical prior information and suffer from uneven training sample distribution due to prevalence. Therefore, we propose a solution that incorporates prior knowledge, addresses the issue of uneven medical sample distribution, and maintains high interpretability in mpMRI. Firstly, we introduce Prior Knowledge-Based Feature Extraction, which mathematically models the PI-RADS criteria for prostate cancer as diagnostic information into model training. Secondly, we propose Adaptive Recall Feedback Loss to address the extremely imbalanced data problem. This method adjusts the training dynamically based on accuracy and recall in the validation set, resulting in high accuracy and recall simultaneously in the testing set.Thirdly, we design an Enhanced Cascade Prostate Cancer Classifier that classifies prostate cancer into different levels in an interpretable way, which refines the classification results and helps with clinical intervention. Our method is validated through experiments on the PI-CAI dataset and outperforms other methods with a more balanced result in both accuracy and recall rate.

cs.CV↗