arXiv subjects

Xinyu Zhu

Publications and source records attributed to Xinyu Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Nonlocal Model for Electron Heat Flux and Self-generated Magnetic Field

Coupling of electron heat conduction and magnetic field takes significant effects in inertial confinement fusion (ICF). As the nonlocal models for electron heat conduction have been developed for modeling kinetic effects on heat flux in hydrodynamic scale, modeling kinetic effects on magnetic field are still restricted to flux limiters instead of nonlocal corrections. We propose a new nonlocal model which can recover the kinetic effects for heat conduction and magnetic field in hydrodynamic scale simultaneously. We clarify the necessity of self-consistently considering the electric field corrections in nonlocal models to get reasonable physical quantities. Using the new nonlocal model, the nonlocal corrections of transport coefficients in magnetized plasma and the magnetic field generation without density gradients are systematically studied. We find nonlocal effects significantly change the magnetic field distribution in laser ablation, which potentially influences the hydrodynamic instabilities in ICF.

physics.plasm-ph↗

arXiv2025

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs). Unlike supervised learning, it updates the model using both correct and incorrect samples via policy gradients. To better understand its mechanism, we decompose the learning signal into reinforcing correct responses and penalizing incorrect ones, referred to as Positive and Negative Sample Reinforcement (PSR and NSR), respectively. We train Qwen2.5-Math-7B, Qwen3-4B and Llama-3.1-8B-Instruct on a mathematical reasoning dataset and uncover a surprising result: training with only negative samples -- without reinforcing correct responses -- can be highly effective: it consistently improves performance over the base model across the entire Pass@$k$ spectrum $k$ up to 256), often matching or surpassing PPO and GRPO. In contrast, reinforcing only correct responses improves Pass@1 but degrades performance at higher $k$, due to reduced diversity. These inference-scaling trends highlight that solely penalizing incorrect responses may contribute more to performance than previously recognized. Through gradient analysis, we show that NSR works by suppressing incorrect generations and redistributing probability mass toward other plausible candidates, guided by the model's prior beliefs. It refines the model's existing knowledge rather than introducing entirely new behaviors. Building on this insight, we propose a simple variant of the RL objective that upweights NSR, and show that it consistently improves overall Pass@$k$ performance on MATH, AIME 2025, and AMC23. Our code is available at https://github.com/TianHongZXY/RLVR-Decomposed.

cs.CL↗

arXiv2025

Aligning Large Language Models via Fully Self-Synthetic Data

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment, where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. Specifically, SAO first instructs the LLM to engage in persona role-play and generate diverse prompts and responses, which are then self-evaluated for preference optimization. Extensive experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval~2.0, while maintaining strong performance on downstream objective tasks (e.g., question-answering, math reasoning). Our work provides a practical solution for self-improvement in aligning LLMs, and the code for reproducing our results is available at: https://github.com/SJY8460/SAO.

cs.CL↗

arXiv2025

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents

Enabling large language models (LLMs) to utilize search tools offers a promising path to overcoming fundamental limitations such as knowledge cutoffs and hallucinations. Recent work has explored reinforcement learning (RL) for training search-augmented agents that interleave reasoning and retrieval before answering. These approaches usually rely on outcome-based rewards (e.g., exact match), implicitly assuming that optimizing for final answers will also yield effective intermediate search behaviors. Our analysis challenges this assumption: we uncover multiple systematic deficiencies in search that arise under outcome-only training and ultimately degrade final answer quality, including failure to invoke tools, invalid queries, and redundant searches. To address these shortcomings, we introduce DeSA (Decoupling Search-and-Answering), a simple two-stage training framework that explicitly separates search optimization from answer generation. In Stage 1, agents are trained to improve search effectiveness with retrieval recall-based rewards. In Stage 2, outcome rewards are employed to optimize final answer generation. Across seven QA benchmarks, DeSA-trained agents consistently improve search behaviors, delivering substantially higher search recall and answer accuracy than outcome-only baselines. Notably, DeSA outperforms single-stage training approaches that simultaneously optimize recall and outcome rewards, underscoring the necessity of explicitly decoupling the two objectives.

cs.AI↗

arXiv2025

LiLM-RDB-SFC: Lightweight Language Model with Relational Database-Guided DRL for Optimized SFC Provisioning

Effective management of Service Function Chains (SFCs) and optimal Virtual Network Function (VNF) placement are critical challenges in modern Software-Defined Networking (SDN) and Network Function Virtualization (NFV) environments. Although Deep Reinforcement Learning (DRL) is widely adopted for dynamic network decision-making, its inherent dependency on structured data and fixed action rules often limits adaptability and responsiveness, particularly under unpredictable network conditions. This paper introduces LiLM-RDB-SFC, a novel approach combining Lightweight Language Model (LiLM) with Relational Database (RDB) to answer network state queries to guide DRL model for efficient SFC provisioning. Our proposed approach leverages two LiLMs, Bidirectional and Auto-Regressive Transformers (BART) and the Fine-tuned Language Net T5 (FLAN-T5), to interpret network data and support diverse query types related to SFC demands, data center resources, and VNF availability. Results demonstrate that FLAN-T5 outperforms BART with a lower test loss (0.00161 compared to 0.00734), higher accuracy (94.79% compared to 80.2%), and less processing time (2h 2min compared to 2h 38min). Moreover, when compared to the large language model SQLCoder, FLAN-T5 matches the accuracy of SQLCoder while cutting processing time by 96% (SQLCoder: 54 h 43 min; FLAN-T5: 2 h 2 min).

cs.NI↗

arXiv2025

SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?

The rapid advancements of AI agents have ignited the long-held ambition of leveraging them to accelerate scientific discovery. Achieving this goal requires a deep understanding of the frontiers of human knowledge. As such, Humanity's Last Exam (HLE) provides an exceptionally challenging touchstone for evaluating scientific AI agents. In this work, we aim to construct the foundational architecture for general-purpose agents and validate the capabilities through leading performance on HLE. To achieve this, we introduce X-Master, a tool-augmented reasoning agent designed to emulate human researchers by interacting flexibly with external tools during its reasoning process. This agent, guided by the conceptualization of code as an interaction language, can flexibly leverage built-in Python libraries and our customized tools to augment the reasoning. We further scale its capabilities through X-Masters, a scattered-and-stacked agentic workflow that systematically enhances breadth and depth of reasoning. Our open-source solution, X-Masters, sets a new state-of-the-art record on HLE with a score of 32.1%, surpassing OpenAI's and Google's Deep Research (26.6% and 26.9%) and becoming the first to exceed the 30% threshold. This work allows us to gain a deeper understanding of complex task-solving and accumulates valuable experience that can inform future advancements, guiding subsequent model training.

cs.AI↗

arXiv2025

AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning

Currently, considerable strides have been achieved in Point-of-Interest (POI) embedding methodologies, driven by the emergence of novel POI tasks like recommendation and classification. Despite the success of task-specific, end-to-end models in POI embedding, several challenges remain. These include the need for more effective multi-context sampling strategies, insufficient exploration of multiple POI contexts, limited versatility, and inadequate generalization. To address these issues, we propose the AdaptGOT model, which integrates both the (Adapt)ive representation learning technique and the Geographical-Co-Occurrence-Text (GOT) representation with a particular emphasis on Geographical location, Co-Occurrence and Textual information. The AdaptGOT model comprises three key components: (1) contextual neighborhood generation, which integrates advanced mixed sampling techniques such as KNN, density-based, importance-based, and category-aware strategies to capture complex contextual neighborhoods; (2) an advanced GOT representation enhanced by an attention mechanism, designed to derive high-quality, customized representations and efficiently capture complex interrelations between POIs; and (3) the MoE-based adaptive encoder-decoder architecture, which ensures topological consistency and enriches contextual representation by minimizing Jensen-Shannon divergence across varying contexts. Experiments on two real-world datasets and multiple POI tasks substantiate the superior performance of the proposed AdaptGOT model.

cs.CL↗

arXiv2025

ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning

As AI capabilities advance toward and potentially beyond human-level performance, a natural transition emerges where AI-driven development becomes more efficient than human-centric approaches. A promising pathway toward this transition lies in AI-for-AI (AI4AI), which leverages AI techniques to automate and optimize the design, training, and deployment of AI systems themselves. While LLM-based agents have shown the potential to realize AI4AI, they are often unable to fully leverage the experience accumulated by agents during the exploration of solutions in the reasoning process, leading to inefficiencies and suboptimal performance. To address this limitation, we propose ML-Master, a novel AI4AI agent that seamlessly integrates exploration and reasoning by employing a selectively scoped memory mechanism. This approach allows ML-Master to efficiently combine diverse insights from parallel solution trajectories with analytical reasoning, guiding further exploration without overwhelming the agent with excessive context. We evaluate ML-Master on the MLE-Bench, where it achieves a 29.3% average medal rate, significantly surpassing existing methods, particularly in medium-complexity tasks, while accomplishing this superior performance within a strict 12-hour time constraint-half the 24-hour limit used by previous baselines. These results demonstrate ML-Master's potential as a powerful tool for advancing AI4AI.

cs.AI↗

arXiv2025

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential token generation process, where each token must be generated before the next can be processed. This sequential dependency restricts the ability to fully leverage modern hardware's parallel processing capabilities. Existing methods like speculative decoding and layer skipping offer potential speedups but have notable drawbacks: speculative decoding relies on an auxiliary "drafter" model, which can be challenging to acquire and increases memory overhead, while layer skipping may introduce discrepancies in the outputs due to the missing key-value cache at skipped layers. In this work, we propose AdaDecode, which accelerates LLM decoding without requiring auxiliary models or changes to the original model parameters, while ensuring output consistency. AdaDecode leverages the insight that many tokens can accurately be generated at intermediate layers, as further layers often do not significantly alter predictions once the model reaches a certain confidence. By adaptively generating tokens at intermediate layers when confidence is high, AdaDecode enables the next token's computation to begin immediately. The remaining layer computations for early-predicted tokens are deferred and executed in parallel with subsequent tokens when needed, maximizing hardware utilization and reducing decoding latency. A final verification step ensures that early predictions match the results of standard autoregressive decoding, preserving output parity. Experiments across diverse generation tasks shows that AdaDecode consistently achieves superior decoding throughput with up to 1.73x speedup, while guaranteeing output parity with standard autoregressive decoding.

cs.CL↗

arXiv2025

RAST: Reasoning Activation in LLMs via Small-model Transfer

Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains intimidatingly resource-intensive, requiring multiple model copies and extensive GPU workloads. On the other hand, while being powerful, recent studies suggest that RL does not fundamentally endow models with new knowledge; rather, it primarily reshapes the model's output distribution to activate reasoning capabilities latent in the base model. Building on this insight, we hypothesize that the changes in output probabilities induced by RL are largely model-size invariant, opening the door to a more efficient paradigm: training a small model with RL and transferring its induced probability shifts to larger base models. To verify our hypothesis, we conduct a token-level analysis of decoding trajectories and find high alignment in RL-induced output distributions across model scales, validating our hypothesis. Motivated by this, we propose RAST, a simple yet effective method that transfers reasoning behaviors by injecting RL-induced probability adjustments from a small RL-trained model into larger models. Experiments across multiple mathematical reasoning benchmarks show that RAST substantially and consistently enhances the reasoning capabilities of base models while requiring significantly lower GPU memory than direct RL training, sometimes even yielding better performance than the RL-trained counterparts. Our findings offer new insights into the nature of RL-driven reasoning and practical strategies for scaling its benefits without incurring its full computational cost. The project page of RAST is available at https://ozyyshr.github.io/RAST/.

cs.LG↗

arXiv2025

Bogolon-mediated electromagnetic wave absorption in multicomponent Bose-Einstein condensates

We investigate the electromagnetic wave absorption process in a coherently coupled two-component Bose-Einstein condensate model in different dimensionality at zero temperature. As the analogue of phonon in the solid state physics, the elementary excitation of the Bose-Einstein condensate is described by Bogoliubov quasiparticle or bogolon for short. Due to the small magnitude of the sound velocity of the bogolon, the absorption process is prohibited by the conservation of energy and momentum. To surmount this depression, the additional degree of freedom must be considered inside of the simple Bose gas model. In this article, we develop a microscopical theory for electromagnetic wave absorption by a two-component Bose-Einstein condensate and investigate the absorption rate dependence in different dimensions. Our calculation shows the possibility of manipulating the absorption property by tuning the parameters of the condensates.

cond-mat.quant-gas↗

arXiv2025

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 4,800 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains (e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 201 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of $3$ proprietary models and 14 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4o, InternVL2-Llama3-76B only achieved an average score across Direct Mimic and Customized Mimic tasks of 82.2 and 61.6, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.

cs.SE↗

arXiv2024

Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism. However, the unchosen experts in MoE models do not contribute to the output, potentially leading to underutilization of the model's capacity. In this work, we first conduct exploratory studies to demonstrate that increasing the number of activated experts does not necessarily improve and can even degrade the output quality. Then, we show that output distributions from an MoE model using different routing strategies substantially differ, indicating that different experts do not always act synergistically. Motivated by these findings, we propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. In SCMoE, the next-token probabilities are determined by contrasting the outputs from strong and weak activation using the same MoE model. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding. Experiments on several benchmarks (GSM8K, StrategyQA, MBPP and HumanEval) demonstrate that SCMoE can consistently enhance Mixtral 8x7B's reasoning capability across various domains. For example, it improves the accuracy on GSM8K from 61.79 to 66.94. Moreover, combining SCMoE with self-consistency yields additional gains, increasing major@20 accuracy from 75.59 to 78.31.

cs.CL↗

arXiv2024

Self-Evolving Multi-Agent Collaboration Networks for Software Development

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/.

cs.SE↗

arXiv2024

Prospect of measuring the top quark mass through energy correlators

Reaching a high precision of the top quark mass is an important task of the Large Hadron Collider. We perform a feasibility study of measuring the top quark mass through the three-point energy correlator. The expected sensitivity of the top quark mass in the boosted regime is presented. We further introduce its application to the low top $p_\text{T}$ regime and demonstrate that both the W boson and the top quark masses could be extracted from this single observable. Compared to traditional observables, the energy correlator shows robustness to uncertainties that usually dominate experimental measurements and provides a promising way to improve experimental precision.

hep-ph↗

arXiv2024

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models

Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play crucial roles in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.

cs.CL↗

arXiv2024

A Survey on the Honesty of Large Language Models

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area.

cs.CL↗

arXiv2024

Lifelong Histopathology Whole Slide Image Retrieval via Distance Consistency Rehearsal

Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical practice, the continuously expanding size of WSI databases limits the practical application of the current CBHIR methods. In this paper, we propose a Lifelong Whole Slide Retrieval (LWSR) framework to address the challenges of catastrophic forgetting by progressive model updating on continuously growing retrieval database. Our framework aims to achieve the balance between stability and plasticity during continuous learning. To preserve system plasticity, we utilize local memory bank with reservoir sampling method to save instances, which can comprehensively encompass the feature spaces of both old and new tasks. Furthermore, A distance consistency rehearsal (DCR) module is designed to ensure the retrieval queue's consistency for previous tasks, which is regarded as stability within a lifelong CBHIR system. We evaluated the proposed method on four public WSI datasets from TCGA projects. The experimental results have demonstrated the proposed method is effective and is superior to the state-of-the-art methods.

cs.CV↗