Searcharxiv⌕ Search

arXiv subjects

Yan Yu

Publications and source records attributed to Yan Yu.

At least 19 recordsLinked to original sources

Reliable Evaluation of AI Agents for Investment Research: A Framework for Performance and Validity Assessment

We consider the problem of evaluating AI agents undertaking investment-research tasks, where agents interact with external information sources and computational tools to produce financial analyses and research reports. An important challenge is that the quality of an agent's final output does not necessarily reflect the quality of its execution process, while the reliability of the resulting assessment also depends on the validity of the evaluation procedure. Furthermore, investment-research tasks differ considerably in their requirements for numerical accuracy, information retrieval, financial analysis and supporting evidence, making it difficult to assess agent performance using a uniform set of criteria. We propose a domain-oriented evaluation framework that distinguishes outcome quality from execution quality and accommodates these differences through task-specific criteria, deterministic validators and independent large language model judges. We also introduce an evaluation-validity mechanism that examines the integrity of evaluation inputs, reference information, supporting evidence and grading outputs, with expert review used to resolve identified deficiencies and significant grading disagreements. Numerical results show that the proposed framework can distinguish differences in agent performance across evaluation dimensions, while identifying potential reliability issues in the evaluation process. The associated implementation and evaluation materials will be made available on GitHub.

cs.AI↗

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This recipe, however, is undermined by two findings in agentic tasks: privileged information alone does not always make a teacher reliable, and the benefit of teacher supervision is stage-dependent. We therefore propose RetireOPD (Self-Retiring On-Policy Distillation), which first optimizes a decoupled, skill-conditioned teacher with environment rewards and then trains a skill-free student jointly with RL and OPD. Rather than following a predefined distillation schedule, RetireOPD adopts Adaptive Retirement: the student drops the teacher on its own once their discrepancy stops shrinking and it reaches a target fraction of the teacher's success rate, after which training proceeds with RL alone. Across Qwen2.5 models from 1.5B to 7B, RetireOPD improves ALFWorld success rate over RL baseline by 14.1% to 18.8% and WebShop accuracy by 11.8% to 19.0%, and surpasses its own skill-conditioned teacher in every setting.

cs.CL↗

CMNIE: An Information Extraction Benchmark for Chinese Military News

Structured extraction from Chinese military news supports intelligence analysis, decision-making, and knowledge base construction. However, existing resources provide limited support for joint informa?tion extraction in this domain, especially when events, event arguments, entities, and relations must be modeled together. We present CMNIE, an information extraction benchmark for Chinese military news. Extend?ing military-domain resources beyond document-level event annotations, CMNIE jointly annotates event triggers, event arguments, named enti?ties, and entity relations under a unified domain schema. The dataset contains 13,000 instances collected from public Chinese military news, with manual annotations for 7 event types, 10 argument roles, 7 entity types, and 8 relation types. We evaluate supervised IE models, zero-shot large language models, and fine-tuned LLM-based extraction methods on a shared test set. Experimental results show that CMNIE remains chal?lenging, especially for relation extraction and exact matching of event?argument spans; zero-shot LLMs often identify relevant semantic units but fail to match gold span boundaries exactly. CMNIE provides a stan?dardized benchmark for studying schema adherence, exact span match?ing, and joint structured extraction in specialized Chinese news.

cs.CL↗

(Mis)Understanding Benign Overfitting in Equity Return Prediction

Highly overparameterized models often predict well despite interpolating training data in complex domains, challenging the classical bias--variance tradeoff. We investigate whether this ``benign overfitting'' phenomenon extends to equity return prediction. Consistent with recent statistical theory, we document two key phenomena: first, a double descent pattern in the ridgeless model's prediction risk; and second, that while the optimal ridge model consistently outperforms its ridgeless counterpart, this performance gap becomes negligible at large parameter-to-observation ratios. Ultimately, however, both models fail to outperform a simple historical average. This empirical evidence aligns with our asymptotic results under the null hypothesis of zero slope coefficients, suggesting that standard equity predictors lack true forecasting power---even within highly flexible, nonlinear machine learning architectures. These findings reconcile modern and classical machine learning in asset pricing: in the absence of a true signal, they asymptotically collapse to the historical average benchmark.

stat.ML↗

Comparative analysis of missing data imputation methods for CSST survey: Impact on photometric redshift estimation performance

Improving the accuracy of photometric redshifts (photo-$z$) is essential for reliable statistical studies of cosmology and galaxy evolution. However, missing photometric bands are a common observational challenge that can significantly degrade photo-$z$ estimation accuracy. In this work, we present a systematic evaluation of data imputation methods aimed at improving photo-$z$ performance. We benchmark a range of representative machine learning (ML) and deep learning (DL) architectures, identifying k-nearest neighbors (KNN) and the attention-based SAITS model as the leading performers. These models are then applied to China Space Station Survey Telescope (CSST) mock data to assess their performance under realistic observational conditions. Our results show that KNN yields the highest accuracy under idealized missing completely at random (MCAR) conditions with complete training sets, whereas robustness tests reveal that SAITS significantly outperforms KNN when training data is incomplete or when applied to realistic mixed-mechanism scenarios. We find that domain consistency between training and testing missingness patterns is a prerequisite for optimal performance, highlighting the risks of domain shift in supervised regression tasks. Furthermore, our analysis demonstrates that while general imputation models are highly effective for MCAR and missing at random (MAR) data, they are detrimental when applied to missing not at random (MNAR) data arising from flux limits, as statistical models fail to capture the physical information inherent in these non-detections. Consequently, we advocate for more sophisticated architectures capable of disentangling stochastic missingness from physical non-detections to address these distinct mechanisms individually.

astro-ph.GA↗

Design, Testing, and Commissioning of the Sun Yat-sen University (SYSU) 80 cm Infrared Telescope

The Sun Yat-sen University (SYSU) 80 cm telescope is a new generation near-infrared (NIR) facility in China dedicated to time-domain astronomy, while also serving as a testbed for emerging NIR cameras. Commissioned in October 2024 at the 4100 m Lenghu site on the Tibetan Plateau in China, the telescope adopts a reflective Cassegrain design with two Nasmyth foci for J and K bands. The J band imaging system, initially equipped with a 640 x 512 off-the-shelf InGaAs camera (INS Mars640) and upgraded in June 2025 to a 1280 x 1024 science-grade, deeply cooled camera (YNAOIR), achieves background-limited performance with a dark current of ~ 14 e-/s/pix and a readout noise of ~ 11 e-. The system reaches a limiting magnitude of J ~ 17 mag (Vega system) in single 20 s exposures and depths of J ~ 19.4 mag with stacked 30 minute exposures. For a variable with J ~ 14 mag during on-sky tests, the system delivers millimagnitude-level photometric precision. Since commissioning, the telescope observed transients such as gamma-ray bursts (GRBs), supernovae and comets, variables including active galactic nuclei (AGNs), high-redshift quasars (z > 6), and brown dwarfs, as well as deep-field imaging reaching J ~ 20.5 mag. This validates the feasibility of using InGaAs cameras for astronomical observations, encouraging other institutions to develop dedicated infrared telescopes or integrate infrared cameras into existing optical telescopes.

astro-ph.IM↗

Identifying Genetic Variants for Obesity: A Knowledge Integration Quantile Regression (KIQR) Approach for Ultra-High-Dimensional Data

Obesity is widely recognized as a serious and pervasive health concern. We study obesity through body mass index (BMI), which is known to be highly heritable, and identify important genetic risk factors for BMI from hundreds of thousands of single nucleotide polymorphisms (SNPs) in the Framingham Study data. Several challenges arise when using traditional genome-wide association studies (GWAS): (1) They suffer from a low power due to a combination of a limited number of participants and the stringent genome-wide significance threshold; (2) existing prior knowledge from large meta-analyses may provide valuable guidance but is often underutilized; (3) the one-at-a-time univariate marginal regression framework ignores the joint and conditional nature of genetic effects; (4) GWAS focus solely on mean outcomes, whereas obesity inherently concerns abnormally high BMI levels. To address these challenges, we conduct the analysis by proposing and applying a novel Knowledge Integration Quantile Regression (KIQR) approach via simultaneous variable selection and estimation, focusing on the conditional high quantiles of BMI, which are most relevant to obesity risk, while integrating prior information from large-scale studies such as the GIANT consortium and UK Biobank. Notably, we identified promising novel associations: rs3798696 in \textit{TFAP2A}, rs7070523 in \textit{ITIH5}, and rs178260 in \textit{AIFM3}, which have not previously been reported in the GWAS literature. These findings provide new insights into the genetic architecture of obesity and demonstrate that quantile-based modeling with integrated prior knowledge can potentially uncover novel genes missed by traditional GWAS approaches. An R implementation and simulation scripts are available at: https://github.com/KIQR-submission/KIQR

stat.AP↗

A Robust Geometric Distortion Solution for Main Survey Camera of CSST

The advancement in sensitivity and field of view of next-generation wide-field survey telescopes requires astrometric measurements with high precision, even in the presence of significant geometric distortions. To address this challenge, we develop a Weighted Polynomial Distortion Correction in 2-Phase (WPDC-2P) method. This approach enhances stellar cross-matching, incorporates distance-based weighting into the traditional polynomial fitting, and employs a look-up table to absorb the remaining distortion residuals. Validated on simulated data from the Main Survey Camera of the \emph{Chinese Space Station Survey Telescope} (CSST), incorporating geometric distortions up to approximately $200$ pixels, the method achieves astrometric standard deviation ranging from 0.013 to 0.107 pixels (0.03 pixels for the $g$-1 detector) across all 18 detectors. Under extreme crowding conditions (e.g., globular cluster NGC 2298), the astrometric precision for the $g$-1 detector reaches 0.05-pixel level within the central region ($r_d < 4000$), despite a centroiding precision of $\sim$0.04 pixels. When applied to the Beijing-Arizona Sky Survey data, for which the standard pipeline delivers an astrometric uncertainty of $\sim$20 mas, our method reduces the positional scatter to $ σ_{Δα}=5.494$ mas (0.01 pixels) and $ σ_{Δδ}=9.981$ mas (0.02 pixels) using only a weighted 3rd-order polynomial correction. The method has been integrated into the CSST data processing pipeline and is prepared for further refinement using on-orbit calibration data.

astro-ph.IM↗

ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction

Pairwise evaluation of large language models (LLMs) has become the dominant paradigm for benchmarking open-ended tasks, yet non-transitive preferences, where evaluators prefer A over B, B over C, but C over A, fundamentally undermine ranking reliability. We show that this critical issue stems largely from low-quality data that contains inherently ambiguous preference pairs. To address this challenge, we propose ELSPR, a principled graph-theoretic framework that models pairwise preferences as tournament graphs and systematically identifies problematic training data. ELSPR quantifies non-transitivity through strongly connected components (SCCs) analysis and measures overall preference clarity using a novel normalized directed graph structural entropy metric. Our filtering methodology selectively removes preference data that induce non-transitivity while preserving transitive preferences. Extensive experiments on the AlpacaEval benchmark demonstrate that models fine-tuned on ELSPR-filtered data achieve substantial improvements: a 13.8% reduction in non-transitivity, a 0.088 decrease in structural entropy, and significantly enhanced discriminative power in real-world evaluation systems. Human validation confirms that discarded data exhibit dramatically lower inter-annotator agreement (34.4% vs. 52.6%) and model-human consistency (51.2% vs. 80.6%) compared to cleaned data. These findings establish ELSPR as an effective data self-purification approach for developing more robust, consistent, and human-aligned LLM evaluation systems.

cs.CL↗

MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis

Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on improving data quality for synthesized instruction pairs in English and have facilitated IT of English-centric LLMs. However, data quality issues in multilingual synthesized instruction pairs are even more severe, since the common synthesizing practice is to translate English synthesized data into other languages using machine translation (MT). Besides the known content errors in these English synthesized data, multilingual synthesized instruction data are further exposed to defects introduced by MT and face insufficient localization of the target languages, leading to cultural inequality in trained LLMs. In this paper, we propose MIDB, a Multilingual Instruction Data Booster to automatically address the quality issues in multilingual synthesized data. MIDB is trained on around 36.8k revision examples across 16 languages by human linguistic experts, thereby can boost the low-quality data by addressing content errors and MT defects, and improving localization in these synthesized data. Both automatic and human evaluation indicate that not only MIDB steadily improved instruction data quality in 16 languages, but also the instruction-following and cultural-understanding abilities of multilingual LLMs fine-tuned on MIDB-boosted data were significantly enhanced, suggesting an improved linguistic and cultural equality.

cs.CL↗

Cosmic Ray Detection and Rejection for CSST

As a space telescope, the China Space Station Survey Telescope (CSST) will face significant challenges from cosmic ray (CR) contamination. These CRs will severely degrade image quality and further influence scientific analysis. Due to the CSST's sky survey strategy, traditional multi-frame stacking methods become invalid. The limited revisits prompted us to develop an effective single-image CR processing method for CSST. We retrained the DeepCR model based on CSST simulated images and achieved 97.90+-0.18% recall and 98.67+-0.05% precision on CR detection. Moreover, this paper puts forward an innovative morphology-sensitive inpainting method, which focuses more on areas with higher scientific value. We trained a UNet++ model especially on contaminated stellar/galactic areas, alongside adaptive median filtering for background regions. This method achieves effective for CRs with different intensities and different distances from centers of scientific targets. By this approach, the photometric errors of CR-corrected targets could be restricted to the level comparable to those of uncontaminated sources. Also, it increases the detection rate by 13.6% compared to CR masking. This method will provide a robust CR mitigation for next-generation space telescopes.

astro-ph.IM↗

Submillimeter-Accurate 3D Lumbar Spine Reconstruction from Biplanar X-Ray Images: Incorporating a Multi-Task Network and Landmark-Weighted Loss

To meet the clinical demand for accurate 3D lumbar spine assessment in a weight-bearing position, this study presents a novel, fully automatic framework for high-precision 3D reconstruction from biplanar X-ray images, overcoming the limitations of existing methods. The core of this method involves a novel multi-task deep learning network that simultaneously performs lumbar decomposition and landmark detection on the original biplanar radiographs. The decomposition effectively eliminates interference from surrounding tissues, simplifying subsequent image registration, while the landmark detection provides an initial pose estimation for the Statistical Shape Model (SSM), enhancing the efficiency and robustness of the registration process. Building on this, we introduce a landmark-weighted 2D-3D registration strategy. By assigning higher weights to complex posterior structures like the transverse and spinous processes during optimization, this strategy significantly enhances the reconstruction accuracy of the posterior arch. Our method was validated against a gold standard derived from registering CT segmentations to the biplanar X-rays. It sets a new benchmark by achieving sub-millimeter accuracy and completes the full reconstruction and measurement workflow in under 20 seconds, establishing a state-of-the-art combination of precision and speed. This fast and low-dose pipeline provides a powerful automated tool for diagnosing lumbar conditions such as spondylolisthesis and scoliosis in their functional, weight-bearing state.

eess.IV↗

Goal Discovery with Causal Capacity for Efficient Reinforcement Learning

Causal inference is crucial for humans to explore the world, which can be modeled to enable an agent to efficiently explore the environment in reinforcement learning. Existing research indicates that establishing the causality between action and state transition will enhance an agent to reason how a policy affects its future trajectory, thereby promoting directed exploration. However, it is challenging to measure the causality due to its intractability in the vast state-action space of complex scenarios. In this paper, we propose a novel Goal Discovery with Causal Capacity (GDCC) framework for efficient environment exploration. Specifically, we first derive a measurement of causality in state space, \emph{i.e.,} causal capacity, which represents the highest influence of an agent's behavior on future trajectories. After that, we present a Monte Carlo based method to identify critical points in discrete state space and further optimize this method for continuous high-dimensional environments. Those critical points are used to uncover where the agent makes important decisions in the environment, which are then regarded as our subgoals to guide the agent to make exploration more purposefully and efficiently. Empirical results from multi-objective tasks demonstrate that states with high causal capacity align with our expected subgoals, and our GDCC achieves significant success rate improvements compared to baselines.

cs.LG↗

HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

Recently, large reasoning models have demonstrated strong mathematical and coding abilities, and deep search leverages their reasoning capabilities in challenging information retrieval tasks. Existing deep search works are generally limited to a single knowledge source, either local or the Web. However, enterprises often require private deep search systems that can leverage search tools over both local and the Web corpus. Simply training an agent equipped with multiple search tools using flat reinforcement learning (RL) is a straightforward idea, but it has problems such as low training data efficiency and poor mastery of complex tools. To address the above issue, we propose a hierarchical agentic deep search framework, HierSearch, trained with hierarchical RL. At the low level, a local deep search agent and a Web deep search agent are trained to retrieve evidence from their corresponding domains. At the high level, a planner agent coordinates low-level agents and provides the final answer. Moreover, to prevent direct answer copying and error propagation, we design a knowledge refiner that filters out hallucinations and irrelevant evidence returned by low-level agents. Experiments show that HierSearch achieves better performance compared to flat RL, and outperforms various deep search and multi-source retrieval-augmented generation baselines in six benchmarks across general, finance, and medical domains.

cs.IR↗

Multicolor interband solitons in microcombs

In microcombs, solitons can drive non-soliton-forming modes to induce optical gain. Under specific conditions, a regenerative secondary temporal pulse coinciding in time and space with the exciting soliton pulse will form at a new spectral location. A mechanism involving Kerr-induced pulse interactions has been proposed theoretically, leading to multicolor solitons containing constituent phase-locked pulses. However, the occurrence of this phenomenon requires dispersion conditions that are not naturally satisfied in conventional optical microresonators. Here, we report the experimental observation of multicolor pulses from a single optical pump in a way that is closely related to the concept of multicolor solitons. The individual soliton pulses share the same repetition rate and could potentially be fully phase-locked. They are generated using interband coupling in a compound resonator.

physics.optics↗

Efficient and wavelength-tunable second-harmonic generation towards the green gap

Achieving compact and efficient visible laser sources is crucial for a wide range of applications. However traditional semiconductor laser technology faces difficulties in producing high-brightness green light, leaving a green gap in wavelength coverage. Second-harmonic generation (SHG) offers a promising alternative by converting near-infrared sources to visible wavelengths with high efficiency and spectral purity. Here, we demonstrate efficient and tunable SHG within the green spectrum using a high-Q Si3N4 microresonator. A space-charge grating induced by the photogalvanic effect realizes reconfigurable grating numbers and flexible wavelength tuning. Additionally, grating formation dynamics and competition is observed. These findings underscore the potential of silicon nitride as a robust, integrative platform for on-chip, tunable green light sources.

physics.optics↗

Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning

Multi-task reinforcement learning employs a single policy to complete various tasks, aiming to develop an agent with generalizability across different scenarios. Given the shared characteristics of tasks, the agent's learning efficiency can be enhanced through parameter sharing. Existing approaches typically use a routing network to generate specific routes for each task and reconstruct a set of modules into diverse models to complete multiple tasks simultaneously. However, due to the inherent difference between tasks, it is crucial to allocate resources based on task difficulty, which is constrained by the model's structure. To this end, we propose a Model Evolution framework with Genetic Algorithm (MEGA), which enables the model to evolve during training according to the difficulty of the tasks. When the current model is insufficient for certain tasks, the framework will automatically incorporate additional modules, enhancing the model's capabilities. Moreover, to adapt to our model evolution framework, we introduce a genotype module-level model, using binary sequences as genotype policies for model reconstruction, while leveraging a non-gradient genetic algorithm to optimize these genotype policies. Unlike routing networks with fixed output dimensions, our approach allows for the dynamic adjustment of the genotype policy length, enabling it to accommodate models with a varying number of modules. We conducted experiments on various robotics manipulation tasks in the Meta-World benchmark. Our state-of-the-art performance demonstrated the effectiveness of the MEGA framework. We will release our source code to the public.

cs.AI↗

All-optical computing with beyond 100-GHz clock rates

A computer's clock rate ultimately determines the minimum time between sequential operations or instructions. Despite exponential advances in electronic computer performance owing to Moore's Law and increasingly parallel system architectures, computer clock rates have remained stagnant at $\sim5~\mathrm{GHz}$ for almost two decades. This poses an intractable problem for applications requiring real-time processing or control of ultrafast information systems. Here we break this barrier by proposing and experimentally demonstrating computing based on an end-to-end and all-optical recurrent neural network harnessing the ultrafast nature of linear and nonlinear optical operations while avoiding electronic operations. The all-optical computer realizes linear operations, nonlinear functions, and memory entirely in the optical domain with $>100~\mathrm{GHz}$ clock rates. We experimentally demonstrate a prototypical task of noisy waveform classification as well as perform ultrafast in-situ analysis of the soliton states from integrated optical microresonators. We further illustrate the application of the architecture for generative artificial intelligence based on quantum fluctuations to generate images even in the absence of input optical signals. Our results highlight the potential of all-optical computing beyond what can be achieved with digital electronics by utilizing ultrafast linear, nonlinear, and memory functions and quantum fluctuations.

physics.optics↗