Background Understanding Classical Chinese remains a major challenge in Chinese education, especially in the National College Entrance Examination (NCEE). Although large language models (LLMs) exhibit strong reasoning capabilities, their performance on exam‐style Classical Chinese questions still suffers from instability and limited accuracy. Methods We propose a multiagent reasoning framework based on LLMs for Classical Chinese question answering. For each question type, standardized reasoning procedures are defined, and specialized agents are trained for subtasks including word interpretation, grammatical analysis, translation, and semantic summarization. A two‐round reasoning mechanism, consisting of an initial response followed by refinement using standard answers, is introduced to enhance consistency and robustness. Results Experiments on Gaokao‐style Classical Chinese questions demonstrate that the proposed framework achieves higher accuracy and greater reasoning stability than single‐agent systems and general‐purpose LLMs. In objective tasks, it outperforms strong Chinese‐oriented models such as Qwen‐Max and Baichuan‐4 by up to 6.8%. Conclusions The proposed multiagent framework improves both the interpretability and reliability of LLM‐based Classical Chinese understanding. It shows strong potential for applications in intelligent tutoring systems, curriculum support, and cognitive modeling of human‐like reasoning in educational contexts.

Maneuver provides flexibility for highly squinted synthetic aperture radar (SAR) and also means complicated signal characteristics in the echo, especially for ground moving target imaging (GMTIm). This article analyzes the interaction of parameters between the maneuvering platform and the moving target. The analysis suggests that three key factors should be taken into account: azimuth spectrum aliasing, Doppler centroid ambiguity, and high-order errors. To deal with these challenges, a novel GMTIm methodology for maneuvering platform is presented. The proposed approach employs an advanced parameter estimation method based on the extended generalized high-order ambiguity function (EGHAF), which enables simultaneous estimation of high-order phase coefficients across all orders in low signal-to-noise ratio (SNR) conditions through 2-D extension. Due to the estimation and compensation for higher order phases, which are usually ignored in conventional methods, the proposed method is more suitable for moving target imaging with maneuvering platforms. The superiority of the proposed approach is verified by simulation and real data results.

Owing to its superior capabilities in counter-stealth and anti-jamming, bistatic inverse synthetic aperture radar (Bi-ISAR) has garnered significant attention in both military and civilian applications. However, the variability in the bistatic angle of Bi-ISAR will lead to position-dependent defocusing and geometric distortions in the imaging result. To address these problems, a novel Bi-ISAR space-variant phase error compensation and geometric correction method based on entropy minimization is proposed. Firstly, a space-variant signal model for Bi-ISAR is derived in a short coherent processing interval (CPI). Subsequently, an optimization function is established, utilizing image entropy as the cost function. By applying the Broyden–Fletcher–Goldfarb–Shanno algorithm to solve this optimization problem, the focused imaging result and the space-variant factors can be obtained simultaneously. Utilizing the distortion relationship derived from the focused image, a range-dependent correction function is constructed and applied to perform geometric corrections. Additionally, image scaling can also be performed by using the space-variant factors. Simulated data processing results validate the effectiveness of the proposed method.

The clutter selection strategy based on sliding window in the conventional constant false alarm rate (CFAR) algorithm leads to different clutter qualities between pixels of the same target in complex environment. To solve the problem, this letter proposes an improved CFAR algorithm based on density clustering. First, two-parameter CFAR is used to detect ship targets. Then, density clustering is performed on each detected target pixel based on spatial distance and detection threshold to improve the target detection accuracy. Finally, false alarms caused by speckle noise are eliminated by using the number of times a pixel is clustered. Experimental results show that compared with conventional CFAR algorithm and the superpixel-level CFAR detectors for ship detection in SAR imagery (SP-CFAR), the proposed algorithm achieves a detection accuracy improvement of over 14.8% in heterogeneous clutter scenarios and dense target scenarios, while maintaining a low false alarm rate no higher than 0.13% in strong noise environments.

Hypersonic glide vehicle usually flies in a spiral trajectory to avoid being detected, reconnoitered, or jammed. However, due to its complex flight characteristics, the hypersonic glide vehicle-borne (HGV) synthetic aperture radar (SAR) faces several new challenges, including the complicated geometric model, serious cross-coupling, and significant spatial variation. To address these issues, a precise range model with large maneuvering parameters is first derived on the basis of the kinematic features, indicating that the signal properties change greatly. Then, a novel nonuniform fast Fourier transform (NUFFT)-based approach performed in the 2-D frequency domain is proposed. The cross-coupling terms are decoupled according to Lagrange mean value and the spatial variations are eliminated by 2-D NUFFT operation, which has a high depth-of-focusing and is more effective for HGV SAR with spiral trajectory. The effectiveness of the proposed approach is substantiated through a series of computer simulations and semi-real data experiments.

In airborne forward-looking imaging, the azimuth resolution and the imaging efficiency are important. In this paper, we propose a low-dimension sparse Bayesian learning with Doppler compensation (LDSBL-DC) method to improve the azimuth resolution with a low computational complexity in airborne forward-looking imaging. First, since the variant pitching angle causes the space-variant of the Doppler centroid, the Doppler convolution matrix needs to be constructed in each range cell. We construct a Doppler compensation matrix to eliminate the space-variant of the Doppler centroid. After the Doppler centroid compensation, the Doppler convolution matrix only needs to be constructed once. Second, we propose a low-dimensional projection model based on the singular value decomposition. In the low-dimensional projection model, the high-dimension echo data is compressed to low-dimension data. Finally, combining Doppler centroid compensation and low-dimensional projection model, a new forward-looking imaging model is created, and we introduce sparse Bayesian learning (SBL) to estimate the imaging parameters. In the estimation of the targets’ scattering coefficient, we reduce the computational complexity by the matrix transformation. Several simulations are designed to evaluate the performance of the efficient forward-looking imaging method. The simulation results show the LDSBL-DC method can improve the azimuth resolution with a low computational complexity.

Airborne forward-looking radar (AFLR) imaging has attracted a lot of attention in fields of Earth observation, independent of weather and daytime. However, the forward-looking imaging quality is not very high. To solve this problem, a sparse superresolution imaging algorithm for AFLR with multiple frames space is proposed. Firstly, the echo model for AFLR is introduced. Then, a multiple frame space is constructed to better describe the distribution of noise and targets of the imaging scene. Finally, the forward-looking imaging problem is constructed as the optimization problem, and the Bayesian framework is used to perform the superresolution imaging. Simulation results and real data results are given to verify its effectiveness.

Deconvolution technique can be utilized in the forward-looking radar (FLR). However, the forward-looking imaging performance degenerates greatly due to the effect of high-speed movement of the platform. In this article, an efficient Bayesian forward-looking superresolution imaging algorithm based on Doppler deconvolution in expanded beam space is proposed. First, the Doppler phase information caused by the high-speed platform is fully exploited and the Doppler matrix is integrated with the antenna pattern. The Doppler convolution model of the echo signal for forward-looking is derived in this article. Then, the Doppler phase information is adopted to perform the Doppler deconvolution. Moreover, an expanded beam space is constructed to enhance the sparsity of the imaging scene. The complex Gaussian distribution and the Laplace distribution have been used to model the distribution characteristics of noise and targets in the imaging scene, respectively. Finally, based on the Bayesian framework, the forward-looking imaging problem is converted into the convex optimization problem. The performance assessment based on simulated and experimental data, also in comparison to the conventional real beam, truncated singular value decomposition (TSVD), iterative adaptive approach (IAA) methods, has demonstrated the effectiveness of our proposed algorithm under high-speed platform scenarios.

Traditional forward-looking imaging methods of real aperture radar yield unsatisfactory performance in the presence of outliers. In this article, a method based on variational Bayesian (VB) is proposed to obtain forward-looking imaging in the presence of outliers. First, considering the non-Gaussian property of the imaging noise due to the outliers, we propose to use the Student-$t$distribution to model noise. In this model, the echo signal does not need preprocessing for the outliers. Second, the Laplace hierarchical distribution is introduced to describe the sparsity of the target. Then, the forward-looking imaging problem converts to the optimal problem. Finally, we give the VB derivation to solve the imaging parameter. To illustrate the imaging performance in the presence of outliers, the outliers are randomly added to some angles and the whole scene of the echo signal in the simulations, respectively. From the simulation results, we can see that the proposed method achieves excellent performance for forward-looking imaging in the presence of outliers.

In this study, the authors present an efficient time‐dimension‐reduced track‐before‐detect (TR‐TBD) processor for slow‐moving weak multi‐targets detection in strong clutter environment. In their proposed framework, they elaborate observations from multiple frames (or scans) and resample them in time direction, then distinguish the slow‐moving targets from the clutter in the radon parameter domain by exploiting the fact that different velocities of targets have different skewing angles corresponding to their tracks in the range–time (range–pulse) plane. To further enlarge the skewing angles differences between the slow‐moving targets and the clutter, TR‐TBD is proposed by incorporating the time‐dimension reduction operator. This is very helpful to amplify the skewing angle of slow‐moving targets, while the improvement is very small for the clutter. Therefore, it is much convenient to figure out the slow‐moving weak targets from heavy clutter environment based on their amplified skewing angle differences by setting proper threshold. After detecting the targets, CLEAN‐based track recovery method is proposed to eliminate the false tracks and recover the true tracks. Experimental results on real‐data demonstrate that the proposed algorithm can detect the closely spaced targets and eliminate the false tracks under low signal‐to‐noise ratio and signal‐to‐clutter ratio.

This letter addresses the problem of cross-range superresolution in Doppler beam sharpening (DBS). The coherence of echoes in the azimuth direction and the sparsity of the DBS image in the Doppler domain are fully exploited; thus, a superresolution DBS imaging framework using aperture-extrapolated sparse representation (SR) is proposed. In this framework, aperture extrapolation based on the autoregressive model is utilized to predict the forward and backward information in the azimuth direction, and SR is exploited to extract the Doppler spectrum information. In addition, the resolution ability with different coherent processing intervals is analyzed. The sharpening ratio in this proposed algorithm can be improved by a factor of two or four theoretically in comparison with the conventional DBS imaging method. Experimental results demonstrate that the proposed framework can lead to noticeable performance improvement.

Kernel methods with specifically designed kernel function are suitable for dealing with practical nonlinear problems. However, kernel methods have found limited applications to synthetic aperture radar (SAR) image change detection in that their performances are affected by the inherent multiplicative speckle noise of SAR images. It is known that the spatial-contextual information is helpful in suppressing the degrading effects of the noise. Therefore, a label-information composite kernel (LIC kernel) constructed on the basis of the spatial-contextual information is proposed in this paper for SAR image change detection. A typical spatial information, the output-space label-neighborhood information that is extracted using all labels in the neighborhood of each pixel, may enhance noise immunity, but with inaccurate edge locations simultaneously. Consequently, the anisotropic Gaussian kernel model is utilized for analyzing anisotropic textures of the bitemporal images, and then, a comparison scheme acting on the input-space textures of the bi-temporal images is proposed to supervise the extraction of the output-space label-neighborhood information in the construction of the LIC kernel. The constructed LIC kernel is of good preservation of edge locations of changed areas as well as strong noise immunity. The LIC kernel is updated iteratively with the newest change map outputted from the support vector machine, until the change map converges. Experiments on real SAR images demonstrate the effectiveness of the LIC kernel method and illustrate that it has both strong noise immunity and good preservation of edge locations of changed areas for SAR image change detection.

Change detection can be performed in a supervised manner. However, supervised methods for synthetic aperture radar (SAR) image change detection may suffer from lack of training samples. Therefore, in this letter, a semisupervised support vector machine classifier based on a cluster-neighborhood (CN) kernel is proposed for SAR image change detection. In the proposed method, samples are categorized into two neighborhoods with kernel k-means clustering algorithm. In addition, a CN kernel is constructed based on the composite-ratio kernel using the neighborhood-based statistical features. When a few labeled samples are available, the proposed CN kernel explores the information of unlabeled samples to enhance its discriminative ability and enhance its robustness against speckles. Experimental results on real SAR image change detection demonstrate the effectiveness of the proposed method when a few labeled samples are available.

The triplet Markov field (TMF) model recently proposed is suitable for tackling the nonstationary image segmentation. In this letter, we propose a hierarchical TMF (HTMF) model for unsupervised synthetic aperture radar (SAR) image segmentation. In virtue of the Bayesian inference on the quadtree, the HTMF model captures the global and local image characteristics more precisely in the bottom-up and top-down probability computations. In this way, the underlying spatial structure information is effectively propagated. To model the SAR data related to radar backscattering sources, generalized Gamma distribution is utilized. The effectiveness of the proposed HTMF model is demonstrated by application to simulated data and real SAR image segmentation.