Pai 的 AI 雷达

今日必看

含近几日仍热话题，按时间衰减排序。今天先看 sickn33/agentic-awesome-skills，其次 TabularisDB/tabularis。并行还有 Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw、How to Evaluate AI Agents From Tool Calls to Task Completion。

日期: 2026/09/22
今日条目: 90

往期2026/09/22

全部90 编码代理7 Agent与工具2 个人助理6 模型与评测27 创作成片13 开发与开源16 产品接入19

领域机器人具身8 生信医疗5 法律合规1 教育1 行业观察7 创业者2 独立开发1

更多资讯

#28

A visual large language foundational model for medical image recognition using clinician-contributed online resources

arXiv:2609.06914v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their application in medical settings remains limited by the scarcity of visual ques

arxiv.org打开原文

#29

CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices

arXiv:2609.21344v1 Announce Type: cross Abstract: For Internet of Things (IoT) devices, a secure algorithm alone is not enough: an attacker with physical access can attack the implementation directly, and its flaws are hard to fix once deployed. Large language models (LLMs) are n

arxiv.org打开原文

#30

PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs

arXiv:2609.18120v2 Announce Type: replace-cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, automated testing unaffordable for the smaller organisations that need it

arxiv.org打开原文

#31

PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design

arXiv:2609.21493v1 Announce Type: new Abstract: Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whether an engineering design will work when executed. Existing benchmarks assess sp

arxiv.org打开原文

#32

QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation

arXiv:2609.23139v1 Announce Type: new Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinical perception within a unified interface. We present QwenVLConnector, a Qwen2.5

arxiv.org打开原文

#33

Runtime Authorization for Resources Acquired by AI Agents

arXiv:2609.14744v2 Announce Type: replace Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget, OAuth, mandate, and fulfillment checks can validate transaction conditions w

arxiv.org打开原文

#34

SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models

arXiv:2609.24894v1 Announce Type: new Abstract: Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large language models (MLLMs). Existing approaches process thousands of patch tokens and t

arxiv.org打开原文

#35

SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?

arXiv:2609.21190v1 Announce Type: cross Abstract: Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with held-out test suites, which are inherently incomplete and increasing

arxiv.org打开原文

#36

Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale

arXiv:2609.21257v1 Announce Type: cross Abstract: Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-contained program. Online autoresearch instead spans a

arxiv.org打开原文

#37

SHAFT: A Slack-Compensating, Helical-Buckling-Attenuating Flexible-Shaft Transmission for Lightweight Multi-DoF Manipulation

arXiv:2609.22677v1 Announce Type: new Abstract: Lightweight and slim manipulators enable safe operation in human living environments. Proximal actuation using remote transmission mechanisms, such as wire-driven or Bowden cables, effectively reduces inertia and arm size by relocat

arxiv.org打开原文

#38

AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation

arXiv:2609.23578v1 Announce Type: new Abstract: As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action (VLA) models and world action models (WAMs) still rely on natural-language instr

arxiv.org打开原文

#39

ARCGym: Benchmarking Deep Reinforcement Learning in Autonomous Robotic Colonoscopy

arXiv:2609.22803v1 Announce Type: new Abstract: Simulations for learning-based autonomous colonoscopic navigation focus mainly on fully actuated capsule robots, failing to capture the contact-rich navigation of long and flexible clinical colonoscopes. We present the Autonomous Ro

arxiv.org打开原文

#40

ARSTAG: An Agentic Real2Sim2Real System for Task-Specific Robot Data Generation

arXiv:2609.24563v1 Announce Type: new Abstract: Adapting visuomotor policies to new manipulation tasks often requires substantial manual engineering or teleoperated data collection. Simulation can provide task-specific data at scale, but constructing the scene, designing expert b

arxiv.org打开原文

#41

DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation

arXiv:2609.23103v1 Announce Type: new Abstract: While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility after generation, leaving an object's simulated response unused a

arxiv.org打开原文

#42

Distributed Infrastructure Sensors and Cues for Robotic Fire-Fighting and Safety System on a Lunar Base

arXiv:2609.22786v1 Announce Type: new Abstract: There are renewed efforts to build a lunar base and house a team of astronauts on the Moon for extended periods. However, important challenges remain, such as a rapid-response fire-hazard management system. In the event of a fire or

arxiv.org打开原文

#43

Robot World Models Are Not Invariant to How the Actions Are Written

arXiv:2609.23252v1 Announce Type: new Abstract: A robot policy is trained with one of two action parameterizations: absolute joint targets, or deltas relative to the current state. The choice is a live engineering decision in robot learning, and a world model conditioned on actio

arxiv.org打开原文

#44

Structured World-State Reasoning for Agentic Robotic Search

arXiv:2609.23841v1 Announce Type: new Abstract: Long-horizon robotic search must resolve natural language against heterogeneous, incomplete, and often ambiguous evidence: textual information, prior maps, and observations arriving over time. The core challenge is to contextualize

arxiv.org打开原文

#45

TS-MAMP: A Remanufactured Agricultural Robot with Second-Life EV Components and NMS-Free On-Device Weed Detection

arXiv:2608.02270v2 Announce Type: replace Abstract: Agriculture 4.0 robotic systems improve field efficiency yet remain too capital-intensive for the fragmented smallholdings that dominate global agriculture. Meanwhile, a growing number of retired low-speed electric-vehicle (LSEV

arxiv.org打开原文

#46

3D Gait-Based Autism Classification Using Attention-Enhanced Deep Learning with Cross-Fold Statistical Stability Analysis

arXiv:2609.14159v2 Announce Type: replace Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose early diagnosis remains challenging because conventional clinical assessments are often subjective, time-consuming, and require expert evaluation. Gait provi

arxiv.org打开原文

#47

AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecture

arXiv:2609.21192v1 Announce Type: new Abstract: Organizations deploying agentic artificial intelligence must determine more than whether a model is trustworthy; they must establish what to validate, control, and observe for a use case to deliver its intended outcome while meeting

arxiv.org打开原文

#48

AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos

arXiv:2609.24487v1 Announce Type: new Abstract: In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixel correspondences and then recover object motion from them, ou

arxiv.org打开原文

#49

An Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data

arXiv:2609.21805v1 Announce Type: cross Abstract: Background: Just-in-time adaptive interventions (JITAIs) can use behavioral data to adapt support to changing contexts, but many rely on predefined rules and manual configuration. Objective: We developed a proof-of-concept sleep J

推荐理由个人 AI 代理面向个人场景的代理产品。

arxiv.org打开原文

#50

An Efficient and Effective Watermarking Scheme for the Protection of the Intellectual Property Rights of Video Generative Models

arXiv:2609.23586v1 Announce Type: new Abstract: The rapid development of video generative models (VGMs) has enabled the generation of highly realistic synthetic videos, raising concerns about the intellectual property rights (IPR) of these models. In particular, two closely relat

arxiv.org打开原文

#51

AI 巨头智能体产品竞速与递归自我改进 (RSI) 动态

📌 一句话摘要 OpenAI 计划发布对标 Grok Bot 的个人智能体产品，同时呼吁制定前沿 AI 的全球技术标准，重点关注递归自我改进 (RSI) 的安全。 📝 详细摘要 OpenAI 预计在 DevDay 前发布暂名 "Codex Bot" 的个人智能体产品，旨在追赶 SpaceXAI 的 Grok Bot 和 Meta 的 Muse，实现 AI 队友跨应用工作。同时，OpenAI 呼吁制定前沿 AI 全球标准，聚焦递归自我改进 (RSI)，尽管公开称其尚未实现，但内部数据显示 AI 智能体已能高效产出研究量并完成轻量模型的后训练。此外，文中还提

bestblogs.dev打开原文