arXiv:2611.22136v1 Announce Type: new Abstract: Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, ca…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5461, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
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 …
🧩 Chức năng: Tự động hoá quy trình
Một hệ thống 'second brain' toàn diện tích hợp 35 kỹ năng AI và 10 agents, sử dụng quy trình kiểm chứng V-model để đảm bảo độ chính xác. Rất đáng chú ý nhờ khả năng tự vận hành và kết nối linh hoạt với các công cụ phát triển hiện đại như Cursor và Claude Code.
🧩 Chức năng: Công cụ quanh mô hình ngôn ngữ (prompt/agent)
Records every skill, agent, and tool call of a Claude Code session, and shows which calls share a context and what each one costs in tokens.
arXiv:2611.22017v1 Announce Type: new Abstract: Agent Skills, file-based packages of procedural knowledge that a coding agent can discover and load on demand, are now shipped by every major agent harness, yet the evidence for how much they help comes almost entirely from setting…
arXiv:2611.22171v1 Announce Type: new Abstract: From quantitative research to personal assistance, AI agents act by iteratively generating and executing code. To decouple the agent harness from code execution, many agents offload execution to dedicated systems called code sandbo…
arXiv:2611.22583v1 Announce Type: new Abstract: Tool-using language-model agents must act on information from untrusted emails, webpages, and documents. This creates a central security challenge: malicious instructions and legitimate task directives can arrive through the same i…
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…
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 …
Anthropic phát hành Claude Managed Agents dạng self-hosted, cho phép công ty chạy agent harness, sandbox và credentials trong môi trường nội bộ. Thay đổi lớn cho các agent tự động hóa công việc doanh nghiệp.
arXiv:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…
🧩 Chức năng: Khung/chương trình AI agent tự làm việc nhiều bước
PeerHarness là công cụ giúp đội ngũ bỏ phiếu định nghĩa Agent Skill (một câu lệnh) cho AI coding agents như Claude Code, biến thành quy tắc được đa số đồng thuận mà không cần server.
🧩 Chức năng: Máy chủ MCP — nối công cụ/dữ liệu của bạn vào AI agent
Automate Huawei eNSP labs: generate .topo files, start and stop devices, and push configuration one command at a time with per-command error reporting.
The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of t…
We (GREP.AI, YC F26) are open-sourcing AgentRun and turning it into a full managed agents platform. Read more about it in this post: https://agentrun.ai/blog/introducing-agentrun-run-smarter-ag... . It includes what we originally built for our own agent harness: - Self-improving …
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…
arXiv:2611.15276v1 Announce Type: new Abstract: Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent update…
Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, yet reliable quality judgments, correction pairs, and controlled variations are d…
LLM agents answer questions by calling APIs and trusting the results. An API can fail silently. It ignores part of a request, such as a misnamed filter, yet returns HTTP 200 and a plausible but wrong result. Current fixes, such as checklists, reviewer models and LLM judges, ask t…
arXiv:2611.14844v1 Announce Type: new Abstract: Many advances in ML systems came from breaking an assumption that earlier methods took for granted: speculative decoding dropped the assumption that a model needs one forward pass per token. Yet algorithms rarely state their assump…
arXiv:2611.16110v1 Announce Type: new Abstract: Integrated sensing and communication (ISAC) is a cornerstone of 6G networks, enabling simultaneous data transmission and environmental perception. However, the ubiquitous radiation of sensing waveforms introduces a critical securit…
arXiv:2611.16565v1 Announce Type: new Abstract: We ask whether small, open-weight decision models can support vulnerability discovery in open-source software at scale and what the surrounding system must provide. These models answer a typed question in one forward pass, returnin…
Frontier multimodal models can now control robots zero-shot from images, yet many manipulation tasks depend on contact forces that images cannot show. Bringing force to an API-only frozen model raises two challenges. First, contact evolves much faster than an API model can decide…
Application optimization requires coding agents to discover useful changes and coordinate them across a complete program while preserving the required computation. We introduce Accelerate Bench, a benchmark of 32 CPU optimization tasks adapted from scientific applications and sup…
arXiv:2611.17814v1 Announce Type: new Abstract: With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product catego…
🧩 Chức năng: Đọc/xử lý tài liệu, PDF, OCR
MOKI资料库 for DeepSeek Harness:本地文件管理、多格式预览与 Office / AI 选区协同编辑。Local file management, rich previews and precise AI editing for DSH.
Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this wor…
arXiv:2611.16103v1 Announce Type: new Abstract: In this paper, we introduce low probability of target detection (LPTD) as a new security objective for wireless sensing systems, where the existence of a target is concealed from passive wardens. Unlike conventional communication s…