We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and beyond. The models lead or are c…
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5392, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.19078v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) problems for heterogeneous teams require agents to collaborate to complete team tasks while making the best use of diverse agent capabilities. We introduce assume/guarantee contracts for he…
arXiv:2611.19333v1 Announce Type: new Abstract: Enterprise information is commonly stored across multiple platforms rather than in one centralized location. Answering questions about workplace activities may require information from several sources, including project documents, …
arXiv:2611.19536v1 Announce Type: new Abstract: AI coding agents now push code, publish packages, call model APIs and operate cloud resources on behalf of developers. They authenticate to these services with the same bearer secrets humans use, personal access tokens, API keys an…
arXiv:2611.18747v1 Announce Type: new Abstract: Multimodal large language models (LLMs) have enabled capable computer-use agents that perceive graphical user interfaces, reason over instructions, and execute actions. However, existing approaches to learning from video demonstrat…
arXiv:2611.19061v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to design, optimize, and operate the infrastructure behind AI training and serving, yet the literature remains fragmented across hardware design, machine learning systems, electron…
arXiv:2611.19886v1 Announce Type: new Abstract: Large Language Model (LLM) agents interact with their environments through tools, reading repositories, running builds, and pushing code. When a tool fails with an ordinary error, such as a rate limit or a timeout, the agent can fa…
arXiv:2611.17797v1 Announce Type: new Abstract: Multimodal agentic coding requires robust visual reasoning to analyze observations and evaluate generated artifacts. Current frameworks largely rely on a Thinking-with-Images paradigm, where agents depend on their intrinsic vision …
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:2611.19237v1 Announce Type: new Abstract: Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call…
arXiv:2611.20765v1 Announce Type: new Abstract: Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically d…
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:2611.18133v1 Announce Type: new Abstract: Large language model (LLM) agents keep a long-term memory that the model itself writes: summaries, extracted facts and embeddings derived from what users said. Deleting a message is therefore not enough: its derivatives, storage re…
We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents…
arXiv:2611.19244v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, AL…
arXiv:2611.19868v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are vulnerable to backdoor attacks introduced through data poisoning, making effective backdoor detection a critical security challenge. In this paper, we uncover a novel connection between VLM halluci…
arXiv:2611.19915v1 Announce Type: new Abstract: Memory-safety vulnerabilities continue to dominate real-world exploit chains despite decades of research into software mitigations. CHERI is a hardware architecture that enforces spatial and temporal memory safety by augmenting poi…
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 …
Efficient batch execution of agent tasks is critical to LLM training and development workflows, including benchmark evaluation, synthetic-data generation, and RL rollouts. Since these tasks alternate between LLM inference and environment interaction, we present coordinated optimi…
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:2611.20528v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to build interactive honeypots, yet existing evaluations mainly assess isolated command outputs and cannot determine whether a system remains believable when later commands depend …
arXiv:2611.15223v1 Announce Type: new Abstract: Large-language model (LLM) agents execute actions on external systems through tool calls, and enterprises deploy runtime controls, such as agent gateways, to check this behavior in real time. However, a control can only evaluate th…
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…
In many long-horizon settings, an agent's own choices create future constraints: committing finite capacity establishes future obligations and forecloses later opportunities. Sustaining performance therefore requires both keeping evolving plans feasible and comparing the value of…
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:2611.13161v1 Announce Type: new Abstract: Effective search and rescue (SAR) operations require autonomous systems capable of coordinating multiple heterogeneous agents, adapting to dynamic hazards, and aligning with human mission intent. Existing language-guided reinforcem…
arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empi…
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:2611.18027v1 Announce Type: new Abstract: Web caches reduce origin load and latency, but automated traffic can either warm them or evict objects shoppers reuse, lowering the cache hit ratio (CHR). Existing bot defenses generally infer automation from User-Agent (UA) string…
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:2611.17696v1 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…
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with bot…
arXiv:2611.18930v1 Announce Type: new Abstract: Safety benchmarks are cited as the primary tool to understand the risks posed by generative AI (GenAI) systems, yet growing evidence suggests they often fail to meet the needs of real-world safety evaluation. We present findings fr…
arXiv:2611.19064v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach to improving the reasoning capabilities of large language models. In tasks such as code generation and instruction following, multiple verifiers…
arXiv:2611.19082v1 Announce Type: new Abstract: The objective of this study is to investigate the role of clinical variables - their breadth, source, and quality - in the development, utility, and generalisability of an AI system for bi-parametric MRI (bpMRI)-based diagnosis of …
arXiv:2611.19116v1 Announce Type: new Abstract: Early-life battery degradation trajectory forecasting aims to predict a battery cell's full state-of-health (SOH) trajectory from its initial charge-discharge cycles, potentially reducing cell qualification and evaluation time from…
arXiv:2611.19165v1 Announce Type: new Abstract: The migration of artificial intelligence from centralized cloud infrastructure to resource-constrained Internet-of-Things (IoT) devices reduces communication latency and improves data locality, but it also tightly couples sensing q…
arXiv:2611.18874v1 Announce Type: new Abstract: The CubeSat Space Protocol (CSP) is widely used for communication in CubeSat missions, yet its security model and attack surface remain largely unexplored. In this work, we present a systematic security analysis of CSP and identify…
arXiv:2611.19435v1 Announce Type: new Abstract: E-Government platforms, such as government credit platforms, handle highly sensitive personal data, requiring stringent security authentication (e.g., facial recognition, multi-factor verification) that protects users but impedes t…