Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality. Yet there is limited guidance on how harnesses should organize this effort. We …
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5467, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving memory designs. Yet suitable labels are rarely available for new user histories, and m…
Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, they need to recover an earlier task's requirements and partial progress after intervening work. Existi…
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…
arXiv:2610.26913v1 Announce Type: new Abstract: The adoption of Large Language Models for radiology report structuring has been largely dominated by either proprietary cloud-based models or large open models requiring high-end GPUs for deployment, which is a critical bottleneck …
arXiv:2610.27028v1 Announce Type: new Abstract: A poker agent can make a legal move and still make a strategically poor one. We ask whether compact AI agents can exhibit strategic behavior under hidden information and whether preference optimization can improve beyond static and…
arXiv:2610.27099v1 Announce Type: new Abstract: Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions across entire populations remains computationally expensive. Here …
arXiv:2610.26935v1 Announce Type: new Abstract: AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack was caught changes an agent's ability to evade defe…
arXiv:2610.27244v1 Announce Type: new Abstract: Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain configuration files (e.g., AGENTS.md), long-term memory, and reusable skills. Onc…
arXiv:2610.28891v1 Announce Type: new Abstract: Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an…
arXiv:2610.28914v1 Announce Type: new Abstract: Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring…
arXiv:2610.28989v1 Announce Type: new Abstract: Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies in the task agent's prompt does not reliably prevent violations. Training a guard requires examples of tool call…
arXiv:2610.29121v1 Announce Type: new Abstract: A coding agent that rewrites its own scaffold has to choose which proposed edit to expand before that edit has been evaluated, and the search then has to return one agent. Each run fits one linear readout on the parent's steering-s…
arXiv:2610.29869v1 Announce Type: new Abstract: Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, and carrying the summary forward as memory. We show that in popular open-source coding agents this step is an exp…
arXiv:2603.03403v4 Announce Type: replace Abstract: Trusted Execution Environments (TEEs) protect private memory and attest initial code and configuration, but neither constrain nor attest shared channels between TEEs or with the untrusted host. Confidentiality thus depends on t…
arXiv:2610.30443v1 Announce Type: new Abstract: Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across complex, temporally extended tasks with…
arXiv:2610.30485v1 Announce Type: new Abstract: Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction burden. Reducing this burden req…
arXiv:2610.30488v1 Announce Type: new Abstract: World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolve even when the agent takes no action, and are only partial…
arXiv:2610.30573v1 Announce Type: new Abstract: Unlike conventional GUI agents, personalized GUI agents require user preferences to guide sequential execution over changing GUI states. This raises two challenges: determining HOW each preference should alter execution strategy an…
arXiv:2610.30738v1 Announce Type: new Abstract: When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence through incompatible interfaces. We present A…
arXiv:2610.30226v1 Announce Type: new Abstract: Phishing relies on visual deception, traditionally requiring web-development skills or pre-built kits. LLMs erode this barrier by generating functional websites from natural-language prompts, yet prior work does not answer how far …
arXiv:2610.30666v1 Announce Type: new Abstract: LLM-based scam systems increasingly combine adaptive dialogue, persistent context, external tools, and multi-agent coordination to automate personalized fraud. These capabilities also create a resource dependency: every reasoning s…
arXiv:2610.30963v1 Announce Type: new Abstract: Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing detectors provide limited support for the…
arXiv:2610.30218v1 Announce Type: cross Abstract: Modern Android apps extensively rely on native libraries, bridging Java/Kotlin and C/C++ through the Java Native Interface (JNI). This cross-language interoperation, however, exposes the memory-safe Android Runtime to the unsafe …
arXiv:2610.31846v1 Announce Type: new Abstract: Intelligent agents should learn from their mistakes so that experience leads to continuous improvement. Yet today's agents recover from a mistake only temporarily: in-context reflections are easily forgotten across sessions and com…
arXiv:2610.31916v1 Announce Type: new Abstract: A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of tool-using AI agents, isolating recovery decisions from langu…
arXiv:2610.31972v1 Announce Type: new Abstract: Evaluating conversational agents that act on live, mutable enterprise data is hard: replayed sessions drift as backend state changes, and a benchmark built today can silently go stale as the data it describes moves on. We present a…
arXiv:2610.32024v1 Announce Type: new Abstract: Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce BARC-Bench, a collection of 110 tasks across nine simulate…
arXiv:2610.32196v1 Announce Type: new Abstract: Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and requirements can change while an agent is still wo…
arXiv:2610.32245v1 Announce Type: new Abstract: AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve belief? We show that a deployed self-improving science agent …
arXiv:2610.31713v1 Announce Type: new Abstract: Advances in Omni-modal Large Language Models (OLLMs) have enabled increasingly seamless human-AI interaction, but their unified processing of heterogeneous modalities also expands the attack surface, allowing adversaries to exploit…
arXiv:2610.31914v1 Announce Type: new Abstract: An agent that needs a tool needs authority to call it, and every proposal for governing that authority has to answer one question: of two grants that both let the agent finish a task, which one is smaller? Over-privilege benchmarks…
arXiv:2610.32155v1 Announce Type: new Abstract: AI agents increasingly extend their capabilities by invoking third-party skills, where each skill encapsulates instructions, scripts, and resources for agents to execute on demand. This paper reveals that deploying many benign skil…
arXiv:2610.32210v1 Announce Type: new Abstract: Illicit actors exploit Ethereum's deep liquidity and diverse on-chain services to launder criminal proceeds by combining decentralized finance (DeFi) protocols, cross-chain bridges, and mixers in multi-stage processes. Existing ant…
arXiv:2610.33198v1 Announce Type: new Abstract: A neural classifier can fail completely inside a layered defense without any end-to-end number moving. We demonstrate this on BARBICAN, a fail-closed gateway for language-model tool mediation whose arbitration stage spent an entire…
arXiv:2610.33862v1 Announce Type: new Abstract: Distributed Cyber-Physical Systems (CPS) and Edge AI networks increasingly depend on public-key authentication and key-establishment mechanisms that are vulnerable to cryptographically relevant Quantum Computers (QC). Shor's algori…
arXiv:2610.34064v1 Announce Type: new Abstract: Frontier agentic systems are capable of taking misaligned actions that may cause significant harm. Monitoring techniques are developed to oversee these systems in order to detect and prevent dangerous actions. However, current stat…
arXiv:2610.34253v1 Announce Type: new Abstract: AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly hosted code becomes part of the context that shapes the code they write. We show that this Web-borne context c…
arXiv:2610.34435v1 Announce Type: new Abstract: Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attacker. We present CyberDual, an arena for this dual role of AI: attacker agents hide an exploitable bug in real ma…
arXiv:2610.33105v1 Announce Type: new Abstract: Artificial intelligence (AI) is reshaping mechanical engineering (ME), from modeling, simulation, and optimization to diagnostics, design, and technical communication. Drawing on a round-table at the 28th ABCM International Congres…