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 = 5393, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.19215v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionate…
arXiv:2611.19275v1 Announce Type: new Abstract: LLM-based task-oriented agents depend on tools to interact with their environments, but may overlook execution feedback, repeat ineffective calls, or persist with unproductive strategies. These behaviors can hinder agents' ability …
arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…
arXiv:2611.19465v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) security agents requires reproducible environments whose workflow difficulty can be varied and whose failures can be diagnosed. We present VAST (Verifiable Adversarial Scenario Training & Evalu…
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:2611.19598v1 Announce Type: new Abstract: Current multi-agent authorization architectures prioritize system integrity over human outcomes. While recent models successfully prevent privilege escalation, they externalize the cost of failure onto the human operator. Re-center…
arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a ben…
arXiv:2611.20671v1 Announce Type: new Abstract: Tamarin-based formal verification of security protocols requires expert-authored multiset rewriting rules and temporal-logic lemmas. Translating a natural-language protocol description into a complete formal model with an LLM is ha…
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:2611.19108v1 Announce Type: new Abstract: Recently, LLMs have been making headlines, and headway, in mathematical research. Much of this work focuses on proving existing open conjectures. Deciding what to prove is harder and less studied, because of the lack of a clear cri…
arXiv:2611.19295v1 Announce Type: new Abstract: Deception (honeypots, decoys and canary credentials) rests on a simple premise: legitimate users never touch a fake asset, so any touch is a high-confidence signal. We ask whether that premise holds when the attacker is a large lan…
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:2611.20454v1 Announce Type: new Abstract: Latent multi-agent communication directly transfers Key-Value (KV) cache tensors between transformer-based agents, bypassing text serialization entirely. While computationally efficient and reasoning accurate, this communication ch…
arXiv:2611.17539v1 Announce Type: new Abstract: Autonomous crystal-structure determination from powder X-ray diffraction (pXRD) remains a key bottleneck for self-driving materials laboratories. We formulate the task of pXRD structure determination as a verifiable agentic search …
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:2611.17820v1 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…
arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…
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:2611.17515v1 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:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from …
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:2611.17856v1 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:2611.17918v1 Announce Type: new Abstract: Scaling laws indicate that the generalization error of a large language model (LLM) decreases monotonically with model size once data is sufficient, and the corollary that larger models outperform smaller ones is now widely accepte…
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…
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…
arXiv:2611.18642v1 Announce Type: new Abstract: Agents that work beyond a single context window, or in teams, hand their work to a successor as a short written summary. Evaluation has focused on whether an agent can solve a task, and relatively little is known about how much of …
arXiv:2611.18866v1 Announce Type: new Abstract: In cinematic storytelling, sound and visual transitions do not always coincide in lockstep: dialogue frequently bridges across cuts to reveal reactions or introduces new scenes via J- and L-cuts, while deliberate silences pace the …
arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …
arXiv:2611.19157v1 Announce Type: new Abstract: Grant proposal writing remains a manual, labor-intensive bottleneck: proposals must satisfy rigid, agency-specific templates, and the same intellectual content must be repeatedly re-encoded into incompatible formats across funding …
arXiv:2611.19227v1 Announce Type: new Abstract: Task configurations in factories, warehouses, and everyday physical environments change over time. Physical AI systems therefore need to incorporate new facts into scene memory while preserving valid information about equipment, ob…
arXiv:2611.18887v1 Announce Type: new Abstract: AI agent interoperability protocols enable orchestrators to discover and invoke external agents using machine-readable metadata. In the Agent2Agent (A2A) protocol, Agent Cards contain attacker-controllable natural-language fields t…
arXiv:2611.19551v1 Announce Type: new Abstract: Payment operations requested by an AI agent may remain executable, or their outcomes unresolved, after the agent has stopped. We study when a trusted payment service can account for every payment in an epoch and exclude further pay…
arXiv:2611.20389v1 Announce Type: new Abstract: Execution traces help diagnose AI-agent failures, but sharing them can expose customer identities. For example, detecting that an agent handled the wrong customer's records requires knowing whether the records belong to the request…
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…
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 …
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:2611.12941v1 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:2611.13684v1 Announce Type: new Abstract: Artificial intelligence agents increasingly automate cybersecurity tasks, including offensive operations. Frequent attacks across the web make endpoint detection and response (EDR) a critical defense, but whether AI agents can evad…