arXiv subjects

Zhiwei Xu

Publications and source records attributed to Zhiwei Xu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research lines: 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, versatility and efficiency have appeared fundamentally incompatible to co-achieve, with prior work consistently sacrificing one for the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information is concentrated in localized byte regions, motivating versatile yet efficient localized byte-sequence modeling rather than inefficient global modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing pipeline that directly embeds raw byte sequences. Crucially, to maintain versatility across diverse tasks, we propose a pattern-aware convolutional architecture equipped with dedicated scoring and gating mechanisms. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures. We prototype Nepco on the Nvidia BlueField-3 SmartNIC with multiengine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models, while reducing end-to-end latency by 328x to the millisecond scale.

cs.NI↗

arXiv2026

DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery

Identifying species in biology among tens of thousands of visually similar taxa while discovering unknown species in open-world environments remains a fundamental challenge in biodiversity research. Current methods treat identification and discovery as separate problems, with classification models assuming closed sets and discovery relying on threshold-based rejection. Here we present DeepTaxon, a retrieval-augmented multimodal framework that unifies species identification and discovery through interpretable reasoning over retrieved visual evidence. Given a query image, DeepTaxon retrieves the top-$k$ candidate species with $n$ exemplar images each from a retrieval index and performs chain-of-thought comparative reasoning. Critically, we redefine discovery as an explicit, retrieval-based decision problem rather than an implicit parametric memory problem. A sample is novel if and only if the retrieval index lacks sufficient evidence for identification, so each retrieval naturally yields a classification or discovery label without manual annotation, thereby providing automatic supervision for both tasks. We train the framework via supervised fine-tuning on synthetic retrieval-augmented data, followed by reinforcement learning on hard samples, converting high-recall retrieval into high-precision decisions that scale to massive taxonomic vocabularies. Extensive experiments on a large-scale in-distribution benchmark and six out-of-distribution datasets demonstrate consistent improvements in both identification and discovery. Ablation studies further reveal effective test-time scaling with candidate count $k$ and exemplar count $n$, strong zero-shot transfer to unseen domains, and consistent performance across retrieval encoders, establishing an interpretable solution for biodiversity research.

cs.CV↗

arXiv2026

Reinforced Efficient Reasoning via Semantically Diverse Exploration

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing tree-based reasoning rollouts that enable fine-grained and segment-level credit assignment. However, existing methods still suffer from limited exploration diversity and inefficient reasoning. To address the above challenges, we propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs. To encourage more diverse reasoning exploration, our method incorporates a semantic-entropy-based branching strategy and an $\varepsilon$-exploration mechanism. The former operates on already sampled reasoning rollouts to capture semantic uncertainty and select branching points with high semantic divergence to generate new successive reasoning paths, whereas the latter stochastically initiates reasoning rollouts from the root, preventing the search process from becoming overly local. To improve efficiency, we design a length-aware segment-level advantage estimator that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. Extensive experiments on various mathematical reasoning benchmarks with Qwen and Llama models validate the effectiveness and efficiency of ROSE. Codes are available at https://github.com/ZiqiZhao1/ROSE-rl.

cs.AI↗

arXiv2026

CIR: Lightweight Container Image for Cross-Platform Deployment

In modern cloud and heterogeneous distributed infrastructures, container images are widely used as the deployment unit for machine learning applications. An image bundles the application with its entire platform-specific execution environment and can be directly launched into a container instance. However, this approach forces developers to build and maintain separate images for each target deployment platform. This limitation is particularly evident for widely used interpreted languages such as Python and R in data analytics and machine learning, where application code is inherently cross-platform, yet the runtime dependencies are highly platform-specific. With emerging computing paradigms such as sky computing and edge computing, which demand seamless workload migration and cross-platform deployment, traditional images not only introduce inefficiencies in storage and network usage, but also impose substantial burdens on developers, who must repeatedly craft and manage platform-specific builds. To address these challenges, we propose a lazy-build approach that defers platform-specific construction to the deployment stage, thus keeping the image itself cross-platform. To enable this, we introduce a new image format, CIR (Container Intermediate Representation), together with its pre-builder and lazy-builder. CIR targets interpreted-language applications and only stores the identifiers of the application's direct dependencies, leaving platform adaptation to the lazy-builder, which at deployment time assembles the actual dependencies into runnable containers. A single CIR can therefore be deployed across heterogeneous platforms while reducing image size by 95% compared to conventional images that bundle all dependencies. In our evaluation, CIR reduces deployment time by 40-60% compared with pre-built images, outperforming state-of-the-art systems such as Docker, Buildah, and Apptainer.

cs.DC↗

arXiv2026

Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits

Chinchilla Approach 2 is among the most widely used methods for fitting neural scaling laws. Its parabolic approximation introduces systematic biases in compute-optimal allocation estimates, even on noise-free synthetic data. Applied to published Llama 3 IsoFLOP data at open frontier compute scales, these biases imply a parameter underallocation corresponding to 6.5% of the $3.8\times10^{25}$ FLOP training budget and \$1.4M (90% CI: \$412K-\$2.9M) in unnecessary compute at 50% H100 MFU. Simulated multimodal model misallocations show even greater opportunity costs due to higher loss surface asymmetry. Three sources of this error are examined: IsoFLOP sampling grid width (Taylor approximation accuracy), uncentered IsoFLOP sampling, and loss surface asymmetry ($α\neq β$). Chinchilla Approach 3 largely eliminates these biases but is often regarded as less data-efficient, numerically unstable, prone to local minima, and harder to implement. Each concern is shown to be unfounded or addressable, especially when the partially linear structure of the objective is exploited via Variable Projection, enabling unbiased inference on all five loss surface parameters through a two-dimensional optimization that is well-conditioned, analytically differentiable, and amenable to dense, or even exhaustive, grid search. It may serve as a more convenient replacement for Approach 2 or a more scalable alternative for adaptations of Approach 3 to richer scaling law formulations. See https://github.com/Open-Athena/vpnls for details and https://openathena.ai/scaling-law-analysis for other results from this study.

cs.LG↗

arXiv2026

SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models

Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to-SQL task, significantly outperforming traditional methods.Nevertheless, as a nascent research field, there is still no consensus on the optimal prompt templates and design frameworks. Additionally, existing benchmarks inadequately explore the performance of LLMs across the various sub-tasks of the Text-to-SQL process, which hinders the assessment of LLMs' cognitive capabilities and the optimization of LLM-based solutions. To address the aforementioned issues, we firstly construct a new dataset designed to mitigate the risk of overfitting in LLMs. Then we formulate five evaluation tasks to comprehensively assess the performance of diverse methods across various LLMs throughout the Text-to-SQL process.Our study highlights the performance disparities among LLMs and proposes optimal in-context learning solutions tailored to each task. These findings offer valuable insights for facilitating the development of LLM-based Text-to-SQL systems.

cs.CL↗

arXiv2026

CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation

Ensuring robust and fair interview assessment remains a key challenge in AI-driven evaluation. This paper presents CoMAI, a general-purpose multi-agent interview framework designed for diverse assessment scenarios. In contrast to monolithic single-agent systems based on large language models (LLMs), CoMAI employs a modular task-decomposition architecture coordinated through a centralized finite-state machine. The system comprises four agents specialized in question generation, security, scoring, and summarization. These agents work collaboratively to provide multi-layered security defenses against prompt injection, support multidimensional evaluation with adaptive difficulty adjustment, and enable rubric-based structured scoring that reduces subjective bias. Experimental results demonstrate that CoMAI achieved 90.47% accuracy, 83.33% recall, and 84.41% candidate satisfaction. These results highlight CoMAI as a robust, fair, and interpretable paradigm for AI-driven interview assessment.

cs.MA↗

arXiv2026

QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?

Credit assignment remains a fundamental challenge in multi agent reinforcement learning (MARL) and is commonly addressed through value decomposition under the centralized training with decentralized ex ecution (CTDE) paradigm. However, existing value decomposition meth ods typically rely on predefined mixing networks that require additional training, often leading to imprecise credit attribution and limited in terpretability. We propose QLLM, a novel framework that leverages large language models (LLMs) to construct training-free credit assign ment functions (TFCAFs), where the TFCAFs are nonlinear with re spect to the global state and offer enhanced interpretability while intro ducing no extra learnable parameters. A coder-evaluator framework is employed to ensure the correctness and executability of the generated code. Extensive experiments on standard MARL benchmarks demon strate that QLLM consistently outperforms baselines while requiring fewer learnable parameters. Furthermore, it demonstrates generalization across a broad set of value decomposition algorithms. Code is available at https://github.com/MaoMaoLYJ/pymarl-qllm.

cs.MA↗

arXiv2026

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies. To address this problem, we propose QSIM, a similarity weighted Q-learning framework that reconstructs the TD target using action similarity. Instead of using the greedy joint action directly, QSIM forms a similarity weighted expectation over a structured near-greedy joint action space. This formulation allows the target to integrate Q-values from diverse yet behaviorally related actions while assigning greater influence to those that are more similar to the greedy choice. By smoothing the target with structurally relevant alternatives, QSIM effectively mitigates overestimation and improves learning stability. Extensive experiments demonstrate that QSIM can be seamlessly integrated with various VD methods, consistently yielding superior performance and stability compared to the original algorithms. Furthermore, empirical analysis confirms that QSIM significantly mitigates the systematic value overestimation in MARL. Code is available at https://github.com/MaoMaoLYJ/pymarl-qsim.

cs.MA↗

arXiv2026

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 2.0: a carefully curated hard benchmark composed of 89 tasks in computer terminal environments inspired by problems from real workflows. Each task features a unique environment, human-written solution, and comprehensive tests for verification. We show that frontier models and agents score less than 65\% on the benchmark and conduct an error analysis to identify areas for model and agent improvement. We publish the dataset and evaluation harness to assist developers and researchers in future work at https://www.tbench.ai/ .

cs.SE↗

arXiv2026

Hardwired-Neurons Language Processing Units as General-Purpose Cognitive Substrates

The rapid advancement of Large Language Models (LLMs) has established language as a core general-purpose cognitive substrate, driving the demand for specialized Language Processing Units (LPUs) tailored for LLM inference. To overcome the growing energy consumption of LLM inference systems, this paper proposes a Hardwired-Neurons Language Processing Unit (HNLPU), which physically hardwires LLM weight parameters into the computational fabric, achieving several orders of magnitude computational efficiency improvement by extreme specialization. However, a significant challenge still lies in the scale of modern LLMs. A straightforward hardwiring of gpt-oss 120 B would require fabricating photomask sets valued at over 6 billion dollars, rendering this straightforward solution economically impractical. Addressing this challenge, we propose the novel Metal-Embedding methodology. Instead of embedding weights in a 2D grid of silicon device cells, Metal-Embedding embeds weight parameters into the 3D topology of metal wires. This brings two benefits: (1) a 15x increase in density, and (2) 60 out of 70 photomask layers are homogeneous across chips, including all EUV photomasks. In total, Metal-Embedding reduced the photomask cost by 112x, bringing the Non-Recurring Engineering (NRE) cost of HNLPU into an economically viable range. Experimental results show that HNLPU achieved 249,960 tokens/s (5,555x/85x that of GPU/WSE), 36 tokens/J (1,047x/283x that of GPU/WSE), 13,232 mm2 total die area, $59.46 M-123.5 M estimated NRE at 5 nm technology. Analysis shows that HNLPU achieved 41.7-80.4x improvement in cost-effectiveness and 357x reduction in carbon footprint compared to OpenAI-scale H100 clusters, under an annual weight updating assumption.

cs.AR↗

arXiv2026

Adversarial Contrastive Learning for LLM Quantization Attacks

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after quantization. In this paper, we propose Adversarial Contrastive Learning (ACL), a novel gradient-based quantization attack that achieves superior attack effectiveness by explicitly maximizing the gap between benign and harmful responses probabilities. ACL formulates the attack objective as a triplet-based contrastive loss, and integrates it with a projected gradient descent two-stage distributed fine-tuning strategy to ensure stable and efficient optimization. Extensive experiments demonstrate ACL's remarkable effectiveness, achieving attack success rates of 86.00% for over-refusal, 97.69% for jailbreak, and 92.40% for advertisement injection, substantially outperforming state-of-the-art methods by up to 44.67%, 18.84%, and 50.80%, respectively.

cs.CR↗

arXiv2025

TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement.

cs.AI↗

arXiv2025

Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning

Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignment, which reflects a critical gap between abstract plans and actionable, environment-compatible behaviors. This misalignment arises from two interrelated limitations: (1) LLMs often produce subgoals that are semantically plausible but infeasible or irrelevant in the target environment due to insufficient grounding in environment-specific knowledge, and (2) single-LLM planning conflates generation with self-verification, resulting in overconfident yet unreliable subgoals that frequently fail during execution. To address these challenges, we propose Subgoal Graph-Augmented Actor-Critic-Refiner (SGA-ACR), a framework that integrates an environment-specific subgoal graph and structured entity knowledge with a multi-LLM planning pipeline that explicitly separates generation, critique, and refinement to produce executable and verifiable subgoals. A subgoal tracker further monitors execution progress, provides auxiliary rewards, and adaptively updates the subgoal graph to maintain alignment between plans and actions. Experimental results on 22 diverse tasks in the open-world game "Crafter" demonstrate the effectiveness of our proposed method.

cs.LG↗

arXiv2025

Personalized Image Generation for Recommendations Beyond Catalogs

Personalization is central to human-AI interaction, yet current diffusion-based image generation systems remain largely insensitive to user diversity. Existing attempts to address this often rely on costly paired preference data or introduce latency through Large Language Models. In this work, we introduce REBECA (REcommendations BEyond CAtalogs), a lightweight and scalable framework for personalized image generation that learns directly from implicit feedback signals such as likes, ratings, and clicks. Instead of fine-tuning the underlying diffusion model, REBECA employs a two-stage process: training a conditional diffusion model to sample user- and rating-specific image embeddings, which are subsequently decoded into images using a pretrained diffusion backbone. This approach enables efficient, fine-tuning-free personalization across large user bases. We rigorously evaluate REBECA on real-world datasets, proposing a novel statistical personalization verifier and a permutation-based hypothesis test to assess preference alignment. Our results demonstrate that REBECA consistently produces high-fidelity images tailored to individual tastes, outperforming baselines while maintaining computational efficiency.

cs.IR↗

arXiv2025

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

Large Reasoning Models (LRMs) have demonstrated promising performance in complex tasks. However, the resource-consuming reasoning processes may be exploited by attackers to maliciously occupy the resources of the servers, leading to a crash, like the DDoS attack in cyber. To this end, we propose a novel attack method on LRMs termed ExtendAttack to maliciously occupy the resources of servers by stealthily extending the reasoning processes of LRMs. Concretely, we systematically obfuscate characters within a benign prompt, transforming them into a complex, poly-base ASCII representation. This compels the model to perform a series of computationally intensive decoding sub-tasks that are deeply embedded within the semantic structure of the query itself. Extensive experiments demonstrate the effectiveness of our proposed ExtendAttack. Remarkably, it significantly increases response length and latency, with the former increasing by over 2.7 times for the o3 model on the HumanEval benchmark. Besides, it preserves the original meaning of the query and achieves comparable answer accuracy, showing the stealthiness.

cs.CR↗

arXiv2025

Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs

Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structures, from formal proofs to informal natural language narratives. To address this adaptability gap, we propose the Graph of Verification (GoV), a novel framework for adaptable and multi-granular verification. GoV's core innovation is its flexible "node block" architecture. This mechanism allows GoV to adaptively adjust its verification granularity--from atomic steps for formal tasks to entire paragraphs for natural language--to match the native structure of the reasoning process. This flexibility allows GoV to resolve the fundamental trade-off between verification precision and robustness. Experiments on both well-structured and loosely-structured benchmarks demonstrate GoV's versatility. The results show that GoV's adaptive approach significantly outperforms both holistic baselines and other state-of-the-art decomposition-based methods, establishing a new standard for training-free reasoning verification.

cs.AI↗

arXiv2025

Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild

The proliferation of large language models (LLMs) has significantly advanced intelligent systems. Unfortunately, LLMs often face knowledge conflicts between internal memory and retrieved external information, arising from misinformation, biases, or outdated knowledge. These conflicts undermine response reliability and introduce uncertainty in decision-making. In this work, we analyze how LLMs navigate knowledge conflicts from an information-theoretic perspective and reveal that when conflicting and supplementary information exhibit significant differences, LLMs confidently resolve their preferences and alleviate the uncertainty during their response generation. When this difference is ambiguous, LLMs experience considerable uncertainty about their generation. Based on this insight, we propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models to adapt the retrieved information difference, facilitating robust response generation of LLMs even in conflicting contexts. Extensive experiments confirm our theoretical analysis and demonstrate the performance of Swin-VIB. Notably, Swin-VIB outperforms all competitive baselines in terms of the accuracy of the multiple-choice task, while improving the EM values in the open-ended QA task by at least 11.14%.

cs.CL↗