模型与评测

Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw

arXiv:2609.22067v1 Announce Type: cross Abstract: Users increasingly delegate work to autonomous AI agents, yet evaluations typically measure task completion rather than the values users prioritize. Using Value Sensitive Design, we analyzed, with LLM assistance, 73,093 first-pers

A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems

arXiv:2609.19524v2 Announce Type: replace Abstract: Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (LLMs), agentic systems, and multimodal models (MLLMs) require different forms

Claude Status – Elevated errors for multiple models

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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