arXiv:2611.00463v1 Announce Type: new Abstract: Agent harnesses govern how language models act in an environment; designing their policies by hand is difficult, while automated techniques require representative datasets and costly executions. We present Exo, an agent runtime arc…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5464, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.00518v1 Announce Type: new Abstract: LLMs degrade in multi-turn conversation partly because of context pollution: the model's own earlier outputs stay in context and anchor later turns, so an early misreading of the user's intent can persist after the user corrects it…
arXiv:2611.00713v1 Announce Type: new Abstract: Synthetic variants of known attacks, including feature-space adversarial perturbations, are sometimes used as stand-ins for unseen ("zero-day") attacks when evaluating machine-learning network intrusion detection systems (NIDS). We…
arXiv:2611.01953v1 Announce Type: new Abstract: Existing attacks and defenses for coding agents act once content enters the model context: injected text persuades the model, and guards inspect what the model reads. Yet to judge whether processing an unknown archive, network resp…
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep rese…
arXiv:2611.03930v1 Announce Type: new Abstract: A stored experience may answer one future question and offer little help with another. We measure this task-conditioned utility rather than assigning each memory a single importance score. A task-blind writer stores a memory withou…
arXiv:2611.04048v1 Announce Type: new Abstract: Large Language Models (LLMs) serve both as tools for aiding human decision-making in everyday life and as models of human agents in experimental simulation studies. Alignment on prototypical social decisions -- such as whether to c…
arXiv:2611.04100v1 Announce Type: new Abstract: Harnesses for large language models have converged on a single-threaded shape: one agent, one history, one machine, one sitting. That shape fails work that spans many agents, outlives any one model call, or waits on systems that ar…
arXiv:2611.04126v1 Announce Type: new Abstract: Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting. However, existing methods struggle to effectively utilize these s…
arXiv:2611.04142v1 Announce Type: new Abstract: Web navigation agents built on open-weight language models fail often and fail late, with most of the tokens spent after the trajectory has become unrecoverable. Recent work has shown that early termination is a viable cost-reducti…
arXiv:2611.04289v1 Announce Type: new Abstract: Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynam…
arXiv:2611.04356v1 Announce Type: new Abstract: Finite element method (FEM) solvers are foundational to scientific and engineering simulation, yet their susceptibility to \emph{efficiency attacks} remains largely unexplored. An adversary can craft syntactically valid and runnabl…
arXiv:2611.05391v1 Announce Type: new Abstract: Tool descriptions tell an agent what an action can do, but they do not necessarily reveal whether that action is healthy or suitable at the moment of use. Execution harnesses often possess this information through monitors, traces,…
arXiv:2611.05393v1 Announce Type: new Abstract: Large language models perform strongly on standard medical QA but degrade on harder reasoning tasks, where multi-agent debate often fails to beat strong single-model prompting. We argue that a key limitation is that existing system…
arXiv:2611.05524v1 Announce Type: new Abstract: We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agen…
arXiv:2611.05548v1 Announce Type: new Abstract: We evaluate the extent to which agentic AI models can complete an end-to-end data science project, and how this improves with feedback. A 'writer' model with specific tools creates a complete data science project including download…
arXiv:2611.05650v1 Announce Type: new Abstract: Published explanations of why long-horizon agents fail are commonly taxonomies labeled over completed trajectories: a judge reads a transcript and names the failure. We argue that a claim attributing an agent's behavior to its hist…
arXiv:2611.05662v1 Announce Type: new Abstract: Evaluating open-ended agent tasks increasingly falls to an Agent-as-a-Judge: an evaluator handed tools and the agent's full trajectory so it can verify a result against the environment. The premise is that a judge that gathers its …
arXiv:2611.05753v1 Announce Type: new Abstract: Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances chang…
arXiv:2611.06039v1 Announce Type: new Abstract: Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content. This design makes their control flow vulnerable to prompt injections embedded in webp…
arXiv:2611.06103v1 Announce Type: new Abstract: Sensors bridge the physical and digital worlds, making their integrity critical to cyber-physical system security. Existing sensor attacks largely exploit unintended and sensor-specific physical vulnerabilities, limiting their gene…
arXiv:2611.06989v1 Announce Type: new Abstract: Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (LLMs), orchestration harnesses, and systems of record. Finance receives AI cost only at settlement grain, aggregated by SK…
arXiv:2611.07051v1 Announce Type: new Abstract: Once an agent is live, teams want to know whether it is doing its job, not just whether it throws errors. Yet most evaluation is one-off: a benchmark run, a look at traces, a single score. Its conclusions neither check themselves n…
arXiv:2611.07066v1 Announce Type: new Abstract: Discovering cooperative behavior in multi-agent reinforcement learning (MARL) is challenging due to the combinatorial complexity of joint state-action spaces, which hinders the emergence of coordinated behaviors from trial-and-erro…
arXiv:2611.07247v1 Announce Type: new Abstract: Power matters for AI safety. Optimal agents tend to acquire power across a wide range of objectives (instrumental convergence). As we embed AI agents into socio-technical systems, humans risk gradual disempowerment. Both concerns c…
arXiv:2611.07464v1 Announce Type: new Abstract: Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest. The data must come from the Web, the strategy lives in the user's head, and correctness depends on time, so an agent can fa…
arXiv:2611.07757v1 Announce Type: new Abstract: Enzyme function annotation and the identification of candidate enzymes for a given reaction are essential steps in connecting genomic information to biochemical reaction networks. However, existing methods rely on sequence or struc…
arXiv:2611.07899v1 Announce Type: new Abstract: Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choice affects how retrieval history is maintained, what context each model call receives, and what information must be re-ret…
arXiv:2611.07222v1 Announce Type: new Abstract: Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that l…
arXiv:2611.07640v1 Announce Type: new Abstract: Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent toward an attacker-chosen task. Yet attacker-controlled content can instead tamper with the outcome of the task alr…
arXiv:2611.08613v1 Announce Type: new Abstract: Normative competence, the ability to infer socially enforced expectations from interaction and adjust behavior accordingly, is essential for agents operating in unfamiliar human communities. Yet existing evaluations largely test wh…
arXiv:2611.08666v1 Announce Type: new Abstract: Interactive debuggers are indispensable to human software development, yet coding agents overwhelmingly rely on edit-execute-observe loops, using common bash tools, test scripts, and print statements to debug via repeated shell com…
arXiv:2611.08718v1 Announce Type: new Abstract: Conversational recommender systems often treat user sessions in isolation, limiting their ability to capture how user intent evolves over time. While large language models (LLMs) have improved semantic understanding, they are typic…
arXiv:2611.08811v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are one of the key components of current agentic systems. LRMs augment their output with an explicit chain-of-thought reasoning stage, introducing a new attack surface for thought injection, in which u…
arXiv:2611.08922v1 Announce Type: new Abstract: Automated scientific discovery has the potential to advance understanding of disease mechanisms and accelerate identification of early disease markers. Manual data annotation is infeasible at population scale, motivating methods th…
arXiv:2611.08946v1 Announce Type: new Abstract: Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an …
arXiv:2611.09139v1 Announce Type: new Abstract: This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action…
arXiv:2611.08745v1 Announce Type: new Abstract: Pre-trained machine learning (ML) models shared through public platforms can be weaponized to execute malicious payloads during loading or inference. Existing scanners prove inadequate for detecting malicious models as they rely on…
arXiv:2611.09315v1 Announce Type: new Abstract: Developing cryptographic protocols that are free from vulnerabilities is very challenging, as evidenced by numerous design flaws and implementation bugs in widely used protocols. Recent work has leveraged model checking to generate…
arXiv:2611.09348v1 Announce Type: new Abstract: Reference answers are a supervision channel in text-space Skill optimization, which produces reusable text artifacts called Skills that guide future agent behavior. Poisoning those answers can induce a persistent trigger-conditione…