arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5336, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.17534v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for investigative tasks over incomplete evidence, such as cybersecurity alert triage, but reinforcement learning (RL) for such tasks is difficult: intermediate steps have no v…
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…
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 …
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…
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 …
It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this …
Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a…
arXiv:2611.13196v1 Announce Type: new Abstract: LLM-based agents can reason, use tools and collaborate. However, coordinating increasingly complex agentic applications becomes difficult to understand, monitor and improve. Decisions distributed across prompts, tool calls and appl…
arXiv:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an …
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:2611.10453v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entir…
arXiv:2611.10756v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as shared multi-tenant services, relying on advanced optimizations like KV cache and prefix sharing to improve throughput and reduce latency. However, these optimizations intro…
arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act be…
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:2611.11104v1 Announce Type: new Abstract: As a core protocol for integrating large language models (LLMs) with external data sources and tools, the Model Context Protocol (MCP) has quickly become a key interface in emerging AI agent systems. As the MCP ecosystem expands, r…
arXiv:2611.17819v1 Announce Type: new Abstract: Routine chest computed tomography (CT) captures pulmonary, cardiac, and vascular phenotypes that jointly stratify lung cancer and cardiovascular disease, the two leading causes of death in lung-screening populations. Yet clinical r…
arXiv:2611.17858v1 Announce Type: new Abstract: As Artificial Intelligence (AI)-based systems have become increasingly integrated into various aspects of everyday life, including education, understanding how these systems make decisions is of paramount importance. AI holds signi…
arXiv:2611.17395v1 Announce Type: new Abstract: Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network weights without conventional gradient-based training. While this capability opens …
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:2611.15189v1 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:2611.16588v1 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…
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:2611.13217v1 Announce Type: new Abstract: This study examines the reliability of Claude Code, an agentic deployment of the Claude Opus 4.6 large language model, as a grading system for handwritten university exams. Four research questions addressed agreement with expert hu…
arXiv:2611.13406v1 Announce Type: new Abstract: Autonomous language-model agents can drive industrial controllers over fieldbus protocols, probing a plant at machine speed and in coordinated swarms. We present Talos, an inline gate that judges every agent request to a controller…
arXiv:2611.10542v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules imp…
arXiv:2611.10723v1 Announce Type: new Abstract: Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defens…
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:2611.14949v1 Announce Type: new Abstract: Identifying and solving partial differential equations (PDEs) from sampled solution data often requires substantial expert effort in equation discovery, coefficient estimation, and numerical solver configuration, especially under n…
arXiv:2606.00625v2 Announce Type: replace Abstract: Reproducing software vulnerabilities is fundamental to security researchers, open-source maintainers, and educators. Yet, vulnerabilities are often hard to reproduce, and even when they can be reproduced once, recreating a soft…
arXiv:2611.11399v1 Announce Type: new Abstract: Large Language Models (LLMs) present significant challenges to source tracing of generated code, as LLM rewriting can substantially alter the syntactic and structural characteristics of watermarked code. However, existing watermark…
arXiv:2611.14681v1 Announce Type: new Abstract: Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimizatio…
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:2611.15097v1 Announce Type: new Abstract: Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the informatio…
arXiv:2611.14548v1 Announce Type: new Abstract: Can a coding agent fix a user's repository while also completing and delivering work the user never requested? In this paper, we introduce SideTaskBench to measure this failure where third-party technical references induce agents t…
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…
arXiv:2611.12958v1 Announce Type: new Abstract: Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and …