arXiv subjects

Xinyi Dai

Publications and source records attributed to Xinyi Dai.

At least 19 recordsLinked to original sources

arXiv2026

Cosmological Constraints on the DGP Model in light of DESI DR2 2025 Data

We present updated constraints on both flat and non-flat Dvali-Gabadadze-Porrati (DGP) cosmological models using the latest baryon acoustic oscillation (BAO) measurements from the Dark Energy Spectroscopic Instrument Data Release 2 (DESI DR2), in combination with cosmic chronometer (CC), Type Ia supernova (SNIa), and cosmic microwave background (CMB) distance priors. For the non-flat DGP model, we obtain $H_0 = 64.05 \pm 0.27\, \rm{kms^{-1}Mpc^{-1}}$, $\Omega_m = 0.3264 \pm 0.0043$, and $\Omega_k = 0.0088 \pm 0.0016$, corresponding to a transition redshift $z_t \sim 0.41$. For the flat case, the constraints are $H_0 = 63.28 \pm 0.25\, \rm{kms^{-1}Mpc^{-1}}$ and $\Omega_m = 0.3303 \pm 0.0036$. In both scenarios, the inferred Hubble constant is significantly lower than the Planck $\mathrm{\Lambda}$CDM value, indicating that the DGP framework does not alleviate the Hubble tension. Current observations strongly disfavor the DGP framework, primarily due to its inability to simultaneously accommodate DESI BAO and CMB constraints.By incorporating the latest high-precision DESI observations within a unified analysis framework, this work provides updated and more stringent limits on the DGP scenario, offering a consolidated assessment of its viability in the context of current cosmological data.

astro-ph.CO↗

arXiv2026

Cosmological constraints on the big bang quantum cosmology model

The big bang quantum cosmology model introduces the trace $J$ of the Schouten tensor as a form of dynamic dark energy. Together with cold dark matter, these components form the so-called $J$CDM cosmology model, proposed by M.H.P.M. van Putten (J. High Energy Astrophys., 45, 2025, 194), which offers a potential resolution to the Hubble tension. We derive the constraints on the $J$CDM cosmology model, utilizing early- and late-time cosmological data including cosmic microwave background (CMB), baryon acoustic oscillations (BAO) released by the Dark Energy Spectroscopic Instrument (DESI), cosmic chronometers (CC), and type Ia supernovae (SNIa). For a flat universe, the $J$CDM model yields $ H_0 = 66.95 \pm 0.51 \, \rm{km~s^{-1}~Mpc^{-1}} $ and $ \Omega_m = 0.3419 \pm 0.0065 $, results that are consistent with early-universe observations but exhibit a higher $ \Omega_m $ compared to the $\Lambda$CDM model. In the case of a non-flat universe, $J$CDM favors a slightly curved geometry with $ \Omega_k = 0.0154 \pm 0.0027 $, leading to $ H_0 = 69.13 \pm 0.56 \, \rm {km~s^{-1}~Mpc^{-1}} $ and $ \Omega_m = 0.3477 \pm 0.0074 $. The increase in $ H_0 $ in the non-flat scenario suggests a geometric degeneracy between spatial curvature and $ H_0 $. We also investigate the internal inconsistencies present in DESI data and evaluate their impacts on cosmological parameter constraints. Our analysis shows that while the $J$CDM model, which is constructed from first principles without free parameters beyond those of $\Lambda$CDM, agrees excellently with late-time cosmology, it struggles to simultaneously match early-universe observations in a fully self-consistent manner.

astro-ph.CO↗

arXiv2026

Redshift evolution of the Hubble constant: Constraints and new insights from an interacting dark energy model

We develop a modified interacting dark energy (IDE) model to study the redshift evolution of the Hubble constant ($H_0$), in light of the Hubble tension. In this framework, the energy exchange between dark energy and dark matter induces a redshift dependence of $H_0$. We evaluate the model against a comprehensive suite of observations, including baryon acoustic oscillations (BAO) from DESI DR2 and SDSS, cosmic chronometers, type Ia supernovae from the Pantheon sample, and Planck CMB distance priors. Analysis of late-Universe data yields $\alpha = 0.0107^{+0.0032}_{-0.011}$, with the best-fit value on the order of $10^{-2}$, revealing a decreasing trend of $H_0$ with redshift. This supports a power-law evolution beyond $\Lambda$CDM. Incorporating CMB data further tightens the constraint to the order of $10^{-5}$, which we attribute to the suppression of dark-sector interactions at high redshifts, a consequence of the strong baryon--photon coupling. These results indicate that the IDE framework provides a theoretically consistent and observationally viable mechanism for describing the redshift evolution of $H_0$, offering a promising avenue toward alleviating the Hubble tension.

astro-ph.CO↗

arXiv2026

LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation

Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured tree search, have made progress in exploring reasoning paths but still face two major challenges: (1) underthinking, where reasoning chains tend to be shallow and fail to capture the full complexity of problems; and (2) overthinking, where overly verbose reasoning leads to inefficiency and increased computational costs. To address these issues, we propose LogitsCoder, a novel framework that enhances chain-of-thought reasoning through lightweight, logit-level control mechanisms for code generation. LogitsCoder iteratively generates and refines reasoning steps by first steering token selection toward statistically preferred patterns via Logits Preference Decoding, then selecting and aggregating diverse reasoning paths using Logits Rank Based Path Selection and Thoughts Aggregation. This results in coherent and effective reasoning chains that balance depth and efficiency. Extensive experiments demonstrate that LogitsCoder produces more efficient and higher-quality reasoning chains, leading to superior code generation performance compared to baseline methods.

cs.CL↗

arXiv2025

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Context Support: Built on a dense Multi-Latent Attention (MLA) architecture with a novel STEM-oriented vocabulary, Youtu-LLM supports a 128k context window. This design enables robust long-context reasoning and state tracking within a minimal memory footprint, making it ideal for long-horizon agent and reasoning tasks. (2) Principled "Commonsense-STEM-Agent" Curriculum: We curated a massive corpus of approximately 11T tokens and implemented a multi-stage training strategy. By progressively shifting the pre-training data distribution from general commonsense to complex STEM and agentic tasks, we ensure the model acquires deep cognitive abilities rather than superficial alignment. (3) Scalable Agentic Mid-training: Specifically for the agentic mid-training, we employ diverse data construction schemes to synthesize rich and varied trajectories across math, coding, and tool-use domains. This high-quality data enables the model to internalize planning and reflection behaviors effectively. Extensive evaluations show that Youtu-LLM sets a new state-of-the-art for sub-2B LLMs. On general benchmarks, it achieves competitive performance against larger models, while on agent-specific tasks, it significantly surpasses existing SOTA baselines, demonstrating that lightweight models can possess strong intrinsic agentic capabilities.

cs.CL↗

arXiv2025

ATGen: Adversarial Reinforcement Learning for Test Case Generation

Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised fine-tuning, rely on static datasets. This imposes a ``fixed-difficulty ceiling'', fundamentally limiting their ability to uncover novel or more complex bugs beyond their training scope. To overcome this, we introduce ATGen, a framework that trains a test case generator via adversarial reinforcement learning. ATGen pits a test generator against an adversarial code generator that continuously crafts harder bugs to evade the current policy. This dynamic loop creates a curriculum of increasing difficulty challenging current policy. The test generator is optimized via Reinforcement Learning (RL) to jointly maximize ``Output Accuracy'' and ``Attack Success'', enabling it to learn a progressively stronger policy that breaks the fixed-difficulty ceiling of static training. Extensive experiments demonstrate that ATGen significantly outperforms state-of-the-art baselines. We further validate its practical utility, showing it serves as both a more effective filter for Best-of-N inference and a higher-quality reward source for training code generation models. Our work establishes a new, dynamic paradigm for improving the reliability of LLM-generated code.

cs.SE↗

arXiv2025

DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education

In programming education, Debugging and Teaching (DT) task is a common scenario where students receive assistance in correcting their erroneous code. The task involves multiple inputs, including erroneous code, error messages, reference solutions, and the question description, with the goal of generating modification suggestions to the erroneous code. However, two key challenges hinder the effectiveness of existing approaches. Firstly, the complexity and heterogeneity of inputs inherent in DT tasks significantly elevate the reasoning challenges faced by LLMs. Second, existing approaches often fail to fully leverage the availability of standard code in DT tasks, forcing models to rely solely on complex multi-step reasoning, which limits the potential of LLMs in addressing DT tasks effectively. To address these challenges, we propose DebugTA, a novel LLM-based debugging and teaching agent with specialized tools for standard code retrieval, variable substitution to align reference code, and an external compiler for real-time code analysis. Guided by explicit pedagogical and debugging principles, DebugTA acts as an agent that decomposes a complex task into sequential LLM interactions, each utilizing distinct tools for specific subtasks, thereby simplifying the logical reasoning at each step and reducing overall reasoning complexity. Furthermore, DebugTA utilizes tool calls to align the standard code with the erroneous code as much as possible, allowing the LLM to focus on logic errors within the erroneous code and improving the accuracy of the generated suggestions. To rigorously assess the quality of modification suggestions, we introduce a student simulator-teacher interaction paradigm. Experimental results on three real-world code datasets demonstrate that DebugTA consistently improves teaching effectiveness while significantly reducing computational costs.

cs.SE↗

arXiv2025

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. However, we identify a pervasive length bias in existing PRMs: they tend to assign higher scores to longer reasoning steps, even when the semantic content and logical validity are unchanged. This bias undermines the reliability of reward predictions and leads to overly verbose outputs during inference. To address this issue, we propose CoLD(Counterfactually-Guided Length Debiasing), a unified framework that mitigates length bias through three components: an explicit length-penalty adjustment, a learned bias estimator trained to capture spurious length-related signals, and a joint training strategy that enforces length-invariance in reward predictions. Our approach is grounded in counterfactual reasoning and informed by causal graph analysis. Extensive experiments on MATH500 and GSM-Plus show that CoLD improves accuracy in step selection, and encourages more concise, logically valid reasoning. Furthermore, it consistently improves downstream RL performance and generalizes across domains by mitigating length bias, demonstrating CoLD's strong generalization capability.

cs.CL↗

arXiv2025

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models

Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both query representation and tool retrieval accuracy. MassTool employs a two-tower architecture: a tool usage detection tower that predicts the need for function calls, and a tool retrieval tower that leverages a query-centric graph convolution network (QC-GCN) for effective query-tool matching. It also incorporates search-based user intent modeling (SUIM) to handle diverse and out-of-distribution queries, alongside an adaptive knowledge transfer (AdaKT) module for efficient multi-task learning. By jointly optimizing tool usage detection loss, list-wise retrieval loss, and contrastive regularization loss, MassTool establishes a robust dual-step sequential decision-making pipeline for precise query understanding. Extensive experiments demonstrate its effectiveness in improving retrieval accuracy. Our code is available at https://github.com/wxydada/MassTool.

cs.IR↗

arXiv2025

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Collegiate Programming Contest (ICPC World Finals) and the International Olympiad in Informatics (IOI) spanning 2010 - 2024. As part of HLCE, we design a harmonized online-offline sandbox that guarantees fully reproducible evaluation. Through our comprehensive evaluation, we observe that even the strongest reasoning LLMs: o4-mini(high) and Gemini-2.5 Pro, achieve pass@1 rates of only 15.9% and 11.4%, respectively. Meanwhile, we propose a novel "self-recognition" task to measure LLMs' awareness of their own capabilities. Results indicate that LLMs' self-recognition abilities are not proportionally correlated with their code generation performance. Finally, our empirical validation of test-time scaling laws reveals that current advanced LLMs have substantial room for improvement on complex programming tasks. We expect HLCE to become a milestone challenge for code generation and to catalyze advances in high-performance reasoning and human-AI collaborative programming. Our code and dataset are also public available(https://github.com/Humanity-s-Last-Code-Exam/HLCE).

cs.SE↗

arXiv2025

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.

cs.CL↗

arXiv2025

New cosmological constraints on the evolution of dark matter energy density

We constrain the evolution of dark matter energy density over time, specifically focusing on deviation from the standard model represented by the equation $\rho_{m}\propto(1+z)^{3-\varepsilon}$, where $\varepsilon$ is a constant parameter. Utilizing a diverse array of observational datasets, including baryon acoustic oscillations (BAO) data from the first release of the Dark Energy Spectroscopic Instrument (DESI), distance priors derived from cosmic microwave background (CMB) observations by the Planck satellite, Hubble rate data obtained through the cosmic chronometers (CC) method, type Ia supernova (SNIa) data from the Panthon sample, and the data from the redshift space distortion (RSD) measurements ($f\sigma_8$), we derive stringent constraints on the deviation parameter. We find that for the model under consideration, the deviation parameter is constrained to be $\varepsilon = -0.0073^{+0.0029}_{-0.0033}$, indicating a deviation of approximately $2.4\sigma$ from the scenario where dark matter and vacuum dark energy do not interact. When compared with previous studies and alternative analyses, our findings provide corroborative evidence for an interaction between dark matter and vacuum dark energy, particularly in light of the release of BAO data from DESI.

astro-ph.CO↗

arXiv2025

Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

The improvement of LLMs' instruction-following capabilities depends critically on the availability of high-quality instruction-response pairs. While existing automatic data synthetic methods alleviate the burden of manual curation, they often rely heavily on either the quality of seed data or strong assumptions about the structure and content of web documents. To tackle these challenges, we propose Web Reconstruction (WebR), a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions. Leveraging the inherent diversity of raw web content, we conceptualize web reconstruction as an instruction-tuning data synthesis task via a novel dual-perspective paradigm--Web as Instruction and Web as Response--where each web document is designated as either an instruction or a response to trigger the reconstruction process. Comprehensive experiments show that datasets generated by WebR outperform state-of-the-art baselines by up to 16.65% across four instruction-following benchmarks. Notably, WebR demonstrates superior compatibility, data efficiency, and scalability, enabling enhanced domain adaptation with minimal effort. The data and code are publicly available at https://github.com/YJiangcm/WebR.

cs.CL↗

arXiv2025

Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs

We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field of LLM has been witnessing unprecedented advances in pushing the scale and capability of LLM in recent years, training such a large-scale model still involves significant optimization and system challenges. To stabilize the training process, we propose depth-scaled sandwich normalization, which effectively eliminates loss spikes during the training process of deep models. We pre-train our model on 13.2 trillion diverse and high-quality tokens and further enhance its reasoning capabilities during post-training. To perform such large-scale training efficiently, we utilize 8,192 Ascend NPUs with a series of system optimizations. Evaluations on multiple diverse benchmarks indicate that Pangu Ultra significantly advances the state-of-the-art capabilities of dense LLMs such as Llama 405B and Mistral Large 2, and even achieves competitive results with DeepSeek-R1, whose sparse model structure contains much more parameters. Our exploration demonstrates that Ascend NPUs are capable of efficiently and effectively training dense models with more than 100 billion parameters. Our model and system will be available for our commercial customers.

cs.CL↗

arXiv2025

AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing

Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences. Existing KT models typically follow a single-step training paradigm, which leads to discrepancies with the multi-step inference process required in real-world simulations, resulting in significant error accumulation. This accumulation of error, coupled with the issue of data sparsity, can substantially degrade the performance of recommendation models in the intelligent tutoring systems. To address these challenges, we propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT), which, for the first time, focuses on the multi-step KT task. More specifically, AdvKT leverages adversarial learning paradigm involving a generator and a discriminator. The generator mimics high-reward responses, effectively reducing error accumulation across multiple steps, while the discriminator provides feedback to generate synthetic data. Additionally, we design specialized data augmentation techniques to enrich the training data with realistic variations, ensuring that the model generalizes well even in scenarios with sparse data. Experiments conducted on four real-world datasets demonstrate the superiority of AdvKT over existing KT models, showcasing its ability to address both error accumulation and data sparsity issues effectively.

cs.LG↗

arXiv2025

Cosmological constraints on two vacuum decay models

We constrain two vacuum decay models ($\Lambda(t)$CDM, proposed by the authors of~\cite{Brito:2024bhh}) utilizing the baryon acoustic oscillations (BAO) data released by the Dark Energy Spectroscopic Instrument (DESI), distance prior from the cosmic microwave background (CMB) observed by the Planck satellite, Hubble rate data obtained via the cosmic chronometers (CC) method and type Ia supernova (SNIa) data. The interaction terms between dark matter and dark energy are defined as $Q=3\varepsilon H\rho_{\Lambda}$ for model I and $3\varepsilon aH\rho_{\Lambda}$ for model II. We find that the decay parameter is constrained to be $\varepsilon=0.0094^{+0.0037}_{-0.0033}$ for model I and $\varepsilon=0.0119\pm{0.0045}$ for model II, respectively, indicating a potential interaction between dark matter and dark energy at the $2\sigma$ confidence level. The current Hubble parameter values are estimated to be $H_{0}=70.30\pm{0.67}$ for model I and $H_{0}=70.28\pm{0.64}$ for model II. These values of $H_0$ fall between those derived from the Planck and SH0ES data, suggesting that these two vacuum decay models could provide a potential solution to alleviate the Hubble tension problem.

astro-ph.CO↗

arXiv2025

LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models

Tagging systems play an essential role in various information retrieval applications such as search engines and recommender systems. Recently, Large Language Models (LLMs) have been applied in tagging systems due to their extensive world knowledge, semantic understanding, and reasoning capabilities. Despite achieving remarkable performance, existing methods still have limitations, including difficulties in retrieving relevant candidate tags comprehensively, challenges in adapting to emerging domain-specific knowledge, and the lack of reliable tag confidence quantification. To address these three limitations above, we propose an automatic tagging system LLM4Tag. First, a graph-based tag recall module is designed to effectively and comprehensively construct a small-scale highly relevant candidate tag set. Subsequently, a knowledge-enhanced tag generation module is employed to generate accurate tags with long-term and short-term knowledge injection. Finally, a tag confidence calibration module is introduced to generate reliable tag confidence scores. Extensive experiments over three large-scale industrial datasets show that LLM4Tag significantly outperforms the state-of-the-art baselines and LLM4Tag has been deployed online for content tagging to serve hundreds of millions of users.

cs.IR↗

arXiv2025

Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms in system 2 tasks are not sufficiently explored. Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation and compressing the explored knowledge into System 1 process. In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges: (1) the complex hidden reasoning processes and (2) the heterogeneous data distributions that complicate the exploration and training of robust LLM solvers. To tackle these issues, we propose a novel BDC framework that explores insightful System 2 knowledge of LLMs using a MC-Tree-Of-Agents algorithm with mutual \textbf{B}oosting, \textbf{D}isentangles the heterogeneous training data for composable LoRA-experts, and obtain \textbf{C}ustomized problem solver for each data instance with an input-aware hypernetwork to weight over the LoRA-experts, offering effectiveness, flexibility, and robustness. This framework leverages multiple LLMs through mutual verification and boosting, integrated into a Monte-Carlo Tree Search process enhanced by reflection-based pruning and refinement. Additionally, we introduce the DisenLora algorithm, which clusters heterogeneous data to fine-tune LLMs into composable Lora experts, enabling the adaptive generation of customized problem solvers through an input-aware hypernetwork. This work lays the groundwork for advancing LLM capabilities in complex reasoning tasks, offering a novel System2-to-System1 solution.

cs.AI↗