LLMEval-3: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models

Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting, critical issues that obscure true model capabilities. To address this, we introduce LLMEval-3, a framework for dynamic evaluation of LLMs. LLMEval-3 is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run. Its automated pipeline ensures integrity via contamination-resistant data curation, a novel anti-cheating architecture, and a calibrated LLM-as-a-judge process achieving 90% agreement with human experts, complemented by a relative ranking system for fair comparison. An 20-month longitudinal study of nearly 50 leading models reveals a performance ceiling on knowledge memorization and exposes data contamination vulnerabilities undetectable by static benchmarks. The framework demonstrates exceptional robustness in ranking stability and consistency, providing strong empirical validation for the dynamic evaluation paradigm. LLMEval-3 offers a robust and credible methodology for assessing the true capabilities of LLMs beyond leaderboard scores, promoting the development of more trustworthy evaluation standards.

Physical Adversarial Camouflage through Gradient Calibration and Regularization

The advancement of deep object detectors has greatly affected safety-critical fields like autonomous driving. However, physical adversarial camouflage poses a significant security risk by altering object textures to deceive detectors. Existing techniques struggle with variable physical environments, facing two main challenges: 1) inconsistent sampling point densities across distances hinder the gradient optimization from ensuring local continuity, and 2) updating texture gradients from multiple angles causes conflicts, reducing optimization stability and attack effectiveness. To address these issues, we propose a novel adversarial camouflage framework based on gradient optimization. First, we introduce a gradient calibration strategy, which ensures consistent gradient updates across distances by propagating gradients from sparsely to unsampled texture points. Additionally, we develop a gradient decorrelation method, which prioritizes and orthogonalizes gradients based on loss values, enhancing stability and effectiveness in multi-angle optimization by eliminating redundant or conflicting updates. Extensive experimental results on various detection models, angles and distances show that our method significantly exceeds the state of the art, with an average increase in attack success rate (ASR) of 13.46% across distances and 11.03% across angles. Furthermore, empirical evaluation in real-world scenarios highlights the need for more robust system design.

An Explainable Emotion Alignment Framework for LLM-Empowered Agent in Metaverse Service Ecosystem

Metaverse service is a product of the convergence between Metaverse and service systems, designed to address service-related challenges concerning digital avatars, digital twins, and digital natives within Metaverse. With the rise of large language models (LLMs), agents now play a pivotal role in Metaverse service ecosystem, serving dual functions: as digital avatars representing users in the virtual realm and as service assistants (or NPCs) providing personalized support. However, during the modeling of Metaverse service ecosystems, existing LLM-based agents face significant challenges in bridging virtual-world services with real-world services, particularly regarding issues such as character data fusion, character knowledge association, and ethical safety concerns. This paper proposes an explainable emotion alignment framework for LLM-based agents in Metaverse Service Ecosystem. It aims to integrate factual factors into the decision-making loop of LLM-based agents, systematically demonstrating how to achieve more relational fact alignment for these agents. Finally, a simulation experiment in the Offline-to-Offline food delivery scenario is conducted to evaluate the effectiveness of this framework, obtaining more realistic social emergence.

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

Unsupervised Graph Domain Adaptation (UGDA) leverages labeled source domain graphs to achieve effective performance in unlabeled target domains despite distribution shifts. However, existing methods often yield suboptimal results due to the entanglement of causal-spurious features and the failure of global alignment strategies. We propose SLOGAN (Sparse Causal Discovery with Generative Intervention), a novel approach that achieves stable graph representation transfer through sparse causal modeling and dynamic intervention mechanisms. Specifically, SLOGAN first constructs a sparse causal graph structure, leveraging mutual information bottleneck constraints to disentangle sparse, stable causal features while compressing domain-dependent spurious correlations through variational inference. To address residual spurious correlations, we innovatively design a generative intervention mechanism that breaks local spurious couplings through cross-domain feature recombination while maintaining causal feature semantic consistency via covariance constraints. Furthermore, to mitigate error accumulation in target domain pseudo-labels, we introduce a category-adaptive dynamic calibration strategy, ensuring stable discriminative learning. Extensive experiments on multiple real-world datasets demonstrate that SLOGAN significantly outperforms existing baselines.

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation

Physical adversarial attack methods expose the vulnerabilities of deep neural networks and pose a significant threat to safety-critical scenarios such as autonomous driving. Camouflage-based physical attack is a more promising approach compared to the patch-based attack, offering stronger adversarial effectiveness in complex physical environments. However, most prior work relies on mesh priors of the target object and virtual environments constructed by simulators, which are time-consuming to obtain and inevitably differ from the real world. Moreover, due to the limitations of the backgrounds in training images, previous methods often fail to produce multi-view robust adversarial camouflage and tend to fall into sub-optimal solutions. Due to these reasons, prior work lacks adversarial effectiveness and robustness across diverse viewpoints and physical environments. We propose a physical attack framework based on 3D Gaussian Splatting (3DGS), named PGA, which provides rapid and precise reconstruction with few images, along with photo-realistic rendering capabilities. Our framework further enhances cross-view robustness and adversarial effectiveness by preventing mutual and self-occlusion among Gaussians and employing a min-max optimization approach that adjusts the imaging background of each viewpoint, helping the algorithm filter out non-robust adversarial features. Extensive experiments validate the effectiveness and superiority of PGA. Our code is available at:https://github.com/TRLou/PGA.

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.

Speech-Language Models with Decoupled Tokenizers and Multi-Token Prediction

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the impact of key components (i.e., speech tokenizers, speech heads, and speaker modeling) on the performance of LLM-centric SLMs. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12$\times$ faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness. To address this issue, we draw inspiration from the idea that "the gold standard for supporting a mathematical claim is to provide a proof". We propose a retrospective, step-aware formal verification framework $Safe$. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations. We evaluate our framework $Safe$ across multiple language models and various mathematical datasets, demonstrating a significant performance improvement while offering interpretable and verifiable evidence. We also propose $FormalStep$ as a benchmark for step correctness theorem proving with $30,809$ formal statements. To the best of our knowledge, our work represents the first endeavor to utilize formal mathematical language Lean 4 for verifying natural language content generated by LLMs, aligning with the reason why formal mathematical languages were created in the first place: to provide a robust foundation for hallucination-prone human-written proofs.

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation

Evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error. Current medical benchmarks have three main types: medical exam-based, comprehensive medical, and specialized assessments. However, these benchmarks have limitations in question design (mostly multiple-choice), data sources (often not derived from real clinical scenarios), and evaluation methods (poor assessment of complex reasoning). To address these issues, we present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. We also design an automated evaluation pipeline, incorporating expert-developed checklists into our LLM-as-Judge framework. Furthermore, our methodology validates machine scoring through human-machine agreement analysis, dynamically refining checklists and prompts based on expert feedback to ensure reliability. We evaluate 13 LLMs across three categories (specialized medical models, open-source models, and closed-source models) on LLMEval-Med, providing valuable insights for the safe and effective deployment of LLMs in medical domains. The dataset is released in https://github.com/llmeval/LLMEval-Med.

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation

Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized multimodal evaluation datasets. To advance the development of MLLMs in the finance domain, we introduce FinMME, encompassing more than 11,000 high-quality financial research samples across 18 financial domains and 6 asset classes, featuring 10 major chart types and 21 subtypes. We ensure data quality through 20 annotators and carefully designed validation mechanisms. Additionally, we develop FinScore, an evaluation system incorporating hallucination penalties and multi-dimensional capability assessment to provide an unbiased evaluation. Extensive experimental results demonstrate that even state-of-the-art models like GPT-4o exhibit unsatisfactory performance on FinMME, highlighting its challenging nature. The benchmark exhibits high robustness with prediction variations under different prompts remaining below 1%, demonstrating superior reliability compared to existing datasets. Our dataset and evaluation protocol are available at https://huggingface.co/datasets/luojunyu/FinMME and https://github.com/luo-junyu/FinMME.