arXiv:2611.24983v1 Announce Type: new Abstract: Organizations must decide which vulnerabilities warrant further analysis and protective action when the volume of published vulnerabilities exceeds their analytical capacity. We present a methodology for comparing vulnerability-pri…
⏱ Độ trễ thật của tab này: trung bình 6.3 giờ sau khi CVE được công bố (n = 5287, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
We present Piccolo, a family of multimodal decision models (0.8B to 27B) that coevolves model capabilities and training data via Agentic Data Engineering and recursive self-improvement (RSI). The models predict probabilities over candidate answers for general-purpose text and vis…
arXiv:2611.22179v1 Announce Type: new Abstract: Agentic memory research has accumulated extraction, supersession, reflection, and graph synthesis on top of retrieval-augmented generation. However, we found that almost none of those primitives earn their cost in our tested memory…
arXiv:2611.25228v1 Announce Type: new Abstract: We introduce the Multimodal Knowledge Agent (MKA) benchmark, which measures how well autonomous agents perform end-to-end professional knowledge work that depends on visual understanding. Each task requires an agent to extract and …
arXiv:2611.19465v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) security agents requires reproducible environments whose workflow difficulty can be varied and whose failures can be diagnosed. We present VAST (Verifiable Adversarial Scenario Training & Evalu…
arXiv:2611.19598v1 Announce Type: new Abstract: Current multi-agent authorization architectures prioritize system integrity over human outcomes. While recent models successfully prevent privilege escalation, they externalize the cost of failure onto the human operator. Re-center…
SpecLook đề xuất cách dự đoán (speculate) observation tiếp theo của MLLM agent để giảm vòng lặp zoom‑in, tăng tốc và cung cấp điểm tin cậy cho kết quả.
Bài viết đề xuất khung đánh giá quy trình và provenance cho các autonomous agents thực hiện thí nghiệm ML, nhằm đảm bảo tính minh bạch và kiểm soát lỗi.
arXiv:2611.19230v1 Announce Type: new Abstract: We present CompoundingKernel, a self-improving agent system that writes GPU kernels by search. As of 2026-11-11, its generated kernels rank #1 on the public L1, L2 and Quantization boards of SOL-ExecBench (NVIDIA B200). They have h…
Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to boo…
arXiv:2611.20454v1 Announce Type: new Abstract: Latent multi-agent communication directly transfers Key-Value (KV) cache tensors between transformer-based agents, bypassing text serialization entirely. While computationally efficient and reasoning accurate, this communication ch…
Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortuna…
arXiv:2611.23669v1 Announce Type: new Abstract: Web applications compose the core of internet services, rendering them prominent targets for audacious attackers. Among web attacks, SQL injection (SQLi) remains a persistent, damaging web applications connected to databases. The w…
arXiv:2611.25404v1 Announce Type: new Abstract: AI agents are rapidly evolving from isolated personal assistants into networked actors that interact with one another at scale. We envision the emergence of AI agent societies, with their own social and economic dynamics, as a new …
arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordin…
We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning archite…
arXiv:2611.25087v1 Announce Type: new Abstract: We present SailSearch, a human-guided workflow for algorithmic research with two language-model agents, and report results on Market Split and maximum independent set (MIS). For Market Split, our randomized algorithm searches acros…
arXiv:2611.25135v1 Announce Type: new Abstract: Reinforcement learning (RL) can only teach a language model what its reward can recognize. Answer checkers are exact but need a reference answer; learned reward models and LLM judges work everywhere, but their scores are not probab…
arXiv:2611.25613v1 Announce Type: new Abstract: Although an external language model can select and test repairs to another model's weights, behavior can also be recovered through fixed numerical edits. We assessed the value of interactive selection in a controlled study of Trans…
We introduce Faithfulness Video Score (FVSCORE), a neuro-symbolic framework for specification-driven video generation evaluation. Existing evaluators rely on holistic MLLM judgments or vision-language metrics, yet aligning their scores with human judgments and tracing them to spe…
arXiv:2611.17632v1 Announce Type: new Abstract: Generating an evaluation suite from an agent's specification is diversity-driven search: a generator fills a descriptor space (requirements $\times$ personas $\times$ scenario kinds), and the suite it emits is an archive, then scor…
arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…
arXiv:2611.23564v1 Announce Type: new Abstract: When LLM agents pass intermediate judgments downstream without uncertainty, later decisions may treat tentative assumptions as facts. Effective uncertainty propagation must preserve information for correction and update inherited b…
arXiv:2611.24474v1 Announce Type: new Abstract: Forensic investigators must decide which suspicious files to examine first. Machine-learning (ML) and deep-learning (DL) malware detectors usually return a bare score that neither explains why a file deserves attention nor signals …
arXiv:2611.22103v1 Announce Type: new Abstract: Large language models (LLMs) can now generate Lean proof scripts that capture the high-level structure of many mathematical arguments. However, these scripts frequently fail on complex theorems: a single missing side condition or m…
arXiv:2611.21702v1 Announce Type: new Abstract: Open-weight language models can continue generating after their released weights are modified, while a watermark verifier still scores outputs against the original base and marked models. We study how such modifications change the …
arXiv:2611.22243v1 Announce Type: new Abstract: In LLM serving systems with prefix caching, each KV block of a shared system prompt is held in GPU memory as a single physical copy, which every request with that prompt reads. Our earlier work measured change and showed that one b…
arXiv:2611.19199v1 Announce Type: new Abstract: LoCoMo is a widely reported benchmark for long-term conversational memory, but published scores mix memory quality with choices of answer prompt, judge and baseline layout that are rarely reported together. We measure how much thes…
arXiv:2611.20699v1 Announce Type: new Abstract: Malware detection needs scores calibrated at a fixed false positive rate (FPR) and decisions an analyst can read: feature-based detectors give the first, large language models (LLMs) on decompiled code the second, through generated…
arXiv:2611.25171v1 Announce Type: new Abstract: Test-time compute (TTC) improves language models by spending additional inference compute to generate, verify, and select among candidate outputs, but this recipe has not transferred directly to time series forecasting. A language …
arXiv:2611.25460v1 Announce Type: new Abstract: Training Vision-Language-Action (VLA) models and World-Action Models (WAMs) is computationally expensive, while their heterogeneous architectures and fragmented training stacks make system optimizations difficult to reuse across mo…
arXiv:2611.25568v1 Announce Type: new Abstract: Aerial sensing must combine uncertain overhead context with current observations while budgeting prediction, movement and image processing. AeroBelief uses the next executable action as the unit of verification against reference sc…
arXiv:2611.25664v1 Announce Type: new Abstract: Deep learning models that predict drug--target interactions (DTI) can speed up drug discovery, but the candidate drugs they score are valuable intellectual property that their owners cannot reveal. Secure multiparty computation (MP…
Mixture of Block Attention (MoBA) reduces long-context computation by selecting key-value (KV) blocks for each query. FlashMoBA implements MoBA efficiently but retains a fixed Top-k budget and query-centric schedule. Fixed Top-k applies one budget across different score distribut…
It has been demonstrated that, in certain settings, large language models can perform weight-space programming to directly modify the weights of neural networks. However, it is unknown how dedicated training of these networks can contribute to the successes of weight-space progra…
arXiv:2611.23560v1 Announce Type: new Abstract: Personality is only weakly and inconsistently signaled by written language, and existing text-based methods typically combine language-model and psycholinguistic representations at the input or decision level. It remains open wheth…
arXiv:2611.23702v1 Announce Type: new Abstract: The growing volume of topically similar papers makes it difficult to identify new work that can offer useful research insights or methodological guidance. We present KnowMe Paper Radar, a lightweight discovery tool that combines mu…
arXiv:2611.23350v1 Announce Type: new Abstract: Watermark detectors held by a provider cannot be checked by third parties, and a party that can detect a mark can usually also forge it. We study a two-layer image watermark in which the Fourier transform at the core of the pipelin…
arXiv:2611.23854v1 Announce Type: new Abstract: Physical-layer spoofing detection identifies an attacker who impersonates a legitimate wireless user by checking whether transmissions claiming the same identity originate from different locations, using the received signal strengt…
arXiv:2611.24682v1 Announce Type: new Abstract: Language models judging commands to industrial controllers may not receive machine state, the equipment's current condition. The same command can require opposite safety decisions in different states, so an incorrect answer may ref…