arXiv:2611.25198v1 Announce Type: new Abstract: Every empirical analysis on observational data rests on dozens of defensible analytical choices ("forks") that its readers cannot see. We develop an agentic multiverse analysis (AMA) framework that makes a conclusion's sensitivity …
⏱ Độ trễ thật của tab này: trung bình 6.7 giờ sau khi CVE được công bố (n = 5162, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.25583v1 Announce Type: new Abstract: Large language model (LLM) agents rely on persistent memory to plan tool calls and complete multi-step tasks, which exposes them to memory drift: an adversarial or misleading memory alters the execution path and final outcome. In t…
arXiv:2611.25599v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed for long-running tasks that execute arbitrary shell commands or programs. However, these actions can result in unauthorized network requests or persistent, malicious changes to the use…
arXiv:2611.25718v1 Announce Type: new Abstract: JavaScript programs are often distributed as source code, so attackers can analyze them for vulnerabilities. LLM-based vulnerability detection agents now make this analysis much easier. To mitigate this emerging threat, we present …
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:2611.22075v1 Announce Type: new Abstract: Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabular…
arXiv:2611.23817v1 Announce Type: new Abstract: Coding agents now write whole codebases in long autonomous runs, guided mainly by whether their tests pass. Yet passing tests alone does not reveal accumulating complexity or gaps in test coverage, which then persist as agents exte…
arXiv:2611.23346v1 Announce Type: new Abstract: Long-horizon LLM agents across codebases, web browsers, and enterprise infrastructure rely on an execution harness to move state between the working context, session history, persistent memory, and external environment. While conve…
arXiv:2611.19275v1 Announce Type: new Abstract: LLM-based task-oriented agents depend on tools to interact with their environments, but may overlook execution feedback, repeat ineffective calls, or persist with unproductive strategies. These behaviors can hinder agents' ability …
arXiv:2611.25619v1 Announce Type: new Abstract: Learned models for radio access networks (RANs) are often developed using simulation, yet their predictions can shift when exposed to physical propagation conditions, protocol behavior, and equipment implementations. This paper pre…
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…
Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is …
arXiv:2611.17790v1 Announce Type: new Abstract: Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinfo…
arXiv:2611.17856v1 Announce Type: new Abstract: Tools for interpreting the internal representations of Large Language Models (LLMs) increasingly rely on LLMs themselves to both generate and evaluate explanations, creating a self-referential automated interpretation process with …
arXiv:2611.25790v1 Announce Type: new Abstract: CyberGym evaluates vulnerability reproduction by checking whether a proof-of-concept input (PoC) crashes a vulnerable program version but not a fixed version. Interpreting this differential pass as successful reproduction requires …
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:2611.24489v1 Announce Type: new Abstract: Function-level vulnerability detectors often exhibit fix reversal, assigning a higher vulnerability probability to a fixed version than to its vulnerable counterpart. Fixes usually lengthen functions, and larger length increases ar…
Organizations increasingly deploy downloaded open-weight GUI agents. A backdoored agent passes acceptance tests on clean data and misbehaves only when a visual trigger appears on screen, turning an unvetted checkpoint into a supply-chain risk. However, existing sample-level detec…
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:2611.17793v1 Announce Type: new Abstract: The performance of offline Multi-Agent Reinforcement Learning (MARL) is limited by the quality of the fixed offline dataset, motivating trajectory augmentation. However, augmenting multi-agent trajectories presents a fundamental ch…
arXiv:2611.25086v1 Announce Type: new Abstract: Browsers now ship local language models to ordinary endpoints. Google includes Gemini Nano in Chrome to enable productivity features such as summarization, with inference running entirely on the device. These browser-embedded model…
arXiv:2611.26117v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed as generative inference services, where autoregressive decoding makes response length a key determinant of latency and computational cost. This creates an availability risk: a…
arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…
arXiv:2611.23236v1 Announce Type: cross Abstract: LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection…
arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…
arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models a…
arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standa…
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:2611.23363v1 Announce Type: new Abstract: Publishers often revise and reissue images, yet valid watermarks may persist on superseded releases or unapproved edits. Even a current release can contain regions last authorized at different revisions. We introduce and formalize …
arXiv:2611.23395v1 Announce Type: new Abstract: AIGC watermarking is commonly used for tracing, but it can also support applications such as authentication and tampering detection. We study lossless reversible watermarking, which enables exact recovery of the original watermarke…
arXiv:2611.23602v1 Announce Type: new Abstract: The increasing autonomy of software agents and the proliferation of AI-generated content have weakened the reliability of digital actions as evidence of human involvement. Existing mechanisms, such as digital signatures and authent…
arXiv:2611.24220v1 Announce Type: new Abstract: Existing concept erasure methods for text-to-image diffusion models primarily focus on suppressing target concepts while preserving non-target generation quality. However, in practical applications, open-source diffusion models are…
arXiv:2611.24231v1 Announce Type: new Abstract: Multimodal language models increasingly answer questions over external documents, exposing them to indirect prompt injection: commands planted in untrusted content to hijack the response. Rendering untrusted content as page images …
arXiv:2611.24662v1 Announce Type: new Abstract: AI-driven attacks learn the models of cyber-physical systems (CPS) by passively observing controller and plant signals, then use this knowledge to act covertly. Because covertness depends on the accuracy of the identified model, de…
Rules govern how player actions change interactive worlds. Different rules create distinct gameplay experiences within similar scenes and action spaces. For customizable gameplay, generative world models must follow user-defined rules beyond real-world behaviors. However, realizi…
Video world models keep the world in the context of a generator, so a revisit is synthesized again and earlier edits can drift or disappear. We present WM^MLLM, the first interactive world model built on multimodal large language models (MLLMs), for persistent, editable world gen…
arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants sco…
arXiv:2611.22252v1 Announce Type: new Abstract: Objective. Paper-based assessments are common in patient care, but handwriting and scanning artifacts make these forms difficult to process at scale. This study proposes a modular, multimodal LLM-based system with human oversight f…
arXiv:2611.21951v1 Announce Type: new Abstract: Hate speech remains a persistent and evolving threat on online platforms. The widespread use of large language models (LLMs) further intensifies this problem by making hateful content easier and cheaper to generate at scale. Althou…
arXiv:2611.22186v1 Announce Type: new Abstract: Chat models on phones and laptops are usually 4-bit copies of the model that was evaluated, and audits of such copies disagree about what quantization does to refusal. A 4-bit build is one of many weight perturbations of the same s…