CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source CVE-Factory, LiveCVEBench, Abacus-cve (fine-tuned model), training dataset, and leaderboard. All resources are available at https://github.com/livecvebench/CVE-Factory .

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches, which select a subset of tokens at particular layers to retain in KV cache and prune others, are one of the most popular schemes. They primarily adopt a set of pre-defined layers, at which tokens are selected. Such design is inflexible in the sense that the accuracy significantly varies across tasks and deteriorates in harder tasks such as KV retrieval. In this paper, we propose ASL, a training-free method that adaptively chooses the selection layer for KV cache reduction, exploiting the variance of token ranks ordered by attention score. The proposed method balances the performance across different tasks while meeting the user-specified KV budget requirement. ASL operates during the prefilling stage and can be jointly used with existing KV cache reduction methods such as SnapKV to optimize the decoding stage. By evaluations on the InfiniteBench, RULER, and NIAH benchmarks, we show that equipped with one-shot token selection, where tokens are selected at a layer and propagated to deeper layers, ASL outperforms state-of-the-art layer-wise token selection methods in accuracy while maintaining decoding speed and KV cache reduction.

LLM-Based Social Simulations Require a Boundary

This position paper argues that large language model (LLM)-based social simulations should establish clear boundaries to meaningfully contribute to social science research. While LLMs offer promising capabilities for modeling human-like agents compared to traditional agent-based modeling, they face fundamental limitations that constrain their reliability for social pattern discovery. The core issue lies in LLMs' tendency towards an ``average persona'' that lacks sufficient behavioral heterogeneity, a critical requirement for simulating complex social dynamics. We examine three key boundary problems: alignment (simulated behaviors matching real-world patterns), consistency (maintaining coherent agent behavior over time), and robustness (reproducibility under varying conditions). We propose heuristic boundaries for determining when LLM-based simulations can reliably advance social science understanding. We believe that these simulations are more valuable when focusing on (1) collective patterns rather than individual trajectories, (2) agent behaviors aligning with real population averages despite limited variance, and (3) proper validation methods available for testing simulation robustness. We provide a practical checklist to guide researchers in determining the appropriate scope and claims for LLM-based social simulations.

Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems

Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership. Yet, cross-domain collaboration shatters the unified trust assumptions behind current alignment and containment techniques. An agent benign in isolation may, when receiving messages from an untrusted peer, leak secrets or violate policy, producing risks driven by emergent multi-agent dynamics rather than classical software bugs. This position paper maps the security agenda for cross-domain multi-agent LLM systems. We introduce seven categories of novel security challenges, for each of which we also present plausible attacks, security evaluation metrics, and future research guidelines.

Probabilistic Kernel Function for Fast Angle Testing

In this paper, we study the angle testing problem in high-dimensional Euclidean spaces and propose two projection-based probabilistic kernel functions, one designed for angle comparison and the other for angle thresholding. Unlike existing approaches that rely on random projection vectors drawn from Gaussian distributions, our approach leverages reference angles and employs a deterministic structure for the projection vectors. Notably, our kernel functions do not require asymptotic assumptions, such as the number of projection vectors tending to infinity, and can be both theoretically and experimentally shown to outperform Gaussian-distribution-based kernel functions. We further apply the proposed kernel function to Approximate Nearest Neighbor Search (ANNS) and demonstrate that our approach achieves a 2.5X ~ 3X higher query-per-second (QPS) throughput compared to the state-of-the-art graph-based search algorithm HNSW.

CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics

In this paper, we propose CKGAN, a novel generative adversarial network (GAN) variant based on an integral probability metrics framework with characteristic kernel (CKIPM). CKIPM, as a distance between two probability distributions, is designed to optimize the lowerbound of the maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space, and thus can be used to train GANs. CKGAN mitigates the notorious problem of mode collapse by mapping the generated images back to random noise. To save the effort of selecting the kernel function manually, we propose a soft selection method to automatically learn a characteristic kernel function. The experimental evaluation conducted on a set of synthetic and real image benchmarks (MNIST, CelebA, etc.) demonstrates that CKGAN generally outperforms other MMD-based GANs. The results also show that at the cost of moderately more training time, the automatically selected kernel function delivers very close performance to the best of manually fine-tuned one on real image benchmarks and is able to improve the performances of other MMD-based GANs.

SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity

Free-space trajectory similarity calculation, e.g., DTW, Hausdorff, and Frechet, often incur quadratic time complexity, thus learning-based methods have been proposed to accelerate the computation. The core idea is to train an encoder to transform trajectories into representation vectors and then compute vector similarity to approximate the ground truth. However, existing methods face dual challenges of effectiveness and efficiency: 1) they all utilize Euclidean distance to compute representation similarity, which leads to the severe curse of dimensionality issue -- reducing the distinguishability among representations and significantly affecting the accuracy of subsequent similarity search tasks; 2) most of them are trained in triplets manner and often necessitate additional information which downgrades the efficiency; 3) previous studies, while emphasizing the scalability in terms of efficiency, overlooked the deterioration of effectiveness when the dataset size grows. To cope with these issues, we propose a simple, yet accurate, fast, scalable model that only uses a single-layer vanilla transformer encoder as the feature extractor and employs tailored representation similarity functions to approximate various ground truth similarity measures. Extensive experiments demonstrate our model significantly mitigates the curse of dimensionality issue and outperforms the state-of-the-arts in effectiveness, efficiency, and scalability.

Legal Fact Prediction: Task Definition and Dataset Construction

Legal facts refer to the facts that can be proven by acknowledged evidence in a trial. They form the basis for the determination of court judgments. This paper introduces a novel NLP task: legal fact prediction, which aims to predict the legal fact based on a list of evidence. The predicted facts can instruct the parties and their lawyers involved in a trial to strengthen their submissions and optimize their strategies during the trial. Moreover, since real legal facts are difficult to obtain before the final judgment, the predicted facts also serve as an important basis for legal judgment prediction. We construct a benchmark dataset consisting of evidence lists and ground-truth legal facts for real civil loan cases, LFPLoan. Our experiments on this dataset show that this task is non-trivial and requires further considerable research efforts.

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and efficient personal mobility generation. LLMs overcome the limitations of previous models by efficiently processing semantic data and offering versatility in modeling various tasks. Our approach addresses the critical need to align LLMs with real-world urban mobility data, focusing on three research questions: aligning LLMs with rich activity data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. In experimental studies, comprehensive validation is performed using real-world data. This research marks the pioneering work of designing an LLM agent framework for activity generation based on real-world human activity data, offering a promising tool for urban mobility analysis.

Shall We Talk: Exploring Spontaneous Collaborations of Competing LLM Agents

Recent advancements have shown that agents powered by large language models (LLMs) possess capabilities to simulate human behaviors and societal dynamics. However, the potential for LLM agents to spontaneously establish collaborative relationships in the absence of explicit instructions has not been studied. To address this gap, we conduct three case studies, revealing that LLM agents are capable of spontaneously forming collaborations even within competitive settings. This finding not only demonstrates the capacity of LLM agents to mimic competition and cooperation in human societies but also validates a promising vision of computational social science. Specifically, it suggests that LLM agents could be utilized to model human social interactions, including those with spontaneous collaborations, thus offering insights into social phenomena. The source codes for this study are available at https://github.com/wuzengqing001225/SABM_ShallWeTalk .