Pai 的 AI 雷达
今天：Large Multimodal Models（Agent 原型），Refuses When Asked（Agent 原型）。并行还有 NVIDIA Cosmos3-H-Dreams、AM-Bench、Aptamers as a。
arXiv:2610.28259v1 Announce Type: new Abstract: Recent advances in visuospatial understanding and agentic reasoning enable direct robotic manipulation with general-purpose multimodal models, but their embodied capabilities remain poorly understood. This paper systematically evalu
arXiv:2610.27350v1 Announce Type: cross Abstract: Frontier models can control robots through agent harnesses that loop on one question: what motion comes next toward the user's goal? We show that this default loop carries out harmful instructions. With GPT-6 Astra controlling a l
arXiv:2610.24264v2 Announce Type: replace Abstract: As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions over failure. However, existing safety benchmarks p
arXiv:2610.24806v1 Announce Type: cross Abstract: Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than iterative improvement. Whether large language model (LLM)-b
arXiv:2610.28093v1 Announce Type: cross Abstract: AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not record who may act on this memory, so an instruction hidden in a fetched page can be t
arXiv:2610.27027v1 Announce Type: new Abstract: Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are not the same claim. A clinician acts on the stated reasoning and not on
arXiv:2610.27234v1 Announce Type: new Abstract: Enterprise adoption of LLMs in agentic workflows is gated by evaluations that span a wide arc of abilities: CRM operations, heterogeneous-document retrieval, personal data understanding, multi-turn planning, tool use, function calli
arXiv:2610.26941v1 Announce Type: new Abstract: Large language models (LLMs) are enabling agents to move beyond predefined workflows toward autonomous planning and execution, creating new opportunities for smart manufacturing. However, dynamic environments, complex physical const
arXiv:2610.28286v1 Announce Type: cross Abstract: Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergence guarantees. We formalize collaborative problem solving as
arXiv:2610.28397v1 Announce Type: cross Abstract: Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and a
arXiv:2610.28201v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching the harness space for a specific LLM on a given dataset, RSI c
arXiv:2610.26887v1 Announce Type: new Abstract: Large language model (LLM) agents are evolving from conversational assistants into Cowork Agents capable of autonomous planning, tool use, and complex task execution. Financial analysis requires these agents to integrate cross-docum
arXiv:2610.27377v1 Announce Type: new Abstract: Large language model (LLM) agents now autonomously complete long-horizon tasks, such as repository-level coding, through hundreds of think-act steps, yet the experience each run produces is rarely reused on the next. Prior memory sy
arXiv:2610.27777v1 Announce Type: new Abstract: Tool-using LLM agents increasingly answer e-commerce queries through multi-step tool interactions. The expected output of a tool call can shift between agent development and execution, allowing a plausible but incorrect value to be
arXiv:2610.27704v1 Announce Type: new Abstract: Semantic occupancy mapping supports embodied perception during exploration and detailed scene understanding afterward, giving rise to two complementary requirements: online incremental mapping for maintaining an up-to-date global ma
arXiv:2610.28087v1 Announce Type: new Abstract: AI-generated images linked to news events and online claims can mislead audiences, enable fraud, or cause public controversy. We introduce WildAIGC-Bench, built through recurring collection across news websites, fact-checking source
arXiv:2610.27244v1 Announce Type: cross Abstract: Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain configuration files (e.g., AGENTS.md), long-term memory, and reusable skills. On
arXiv:2610.27199v1 Announce Type: cross Abstract: The Jetson AGX Orin is a common computer for robots and vehicles, yet measured accuracy, speed and energy of current depth estimators on it are hard to find. We benchmark nine model families as of October 2026: the monocular Depth
arXiv:2610.27039v1 Announce Type: new Abstract: Foundation models offer a promising basis for robotic agents, but long-horizon tasks require them to sustain coherent reasoning and reliable physical execution across interdependent stages. We introduce Embodied Playground, a benchm
arXiv:2610.23479v2 Announce Type: replace Abstract: Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls a robot instead of a computer, and where it stops. Our sys
arXiv:2610.28432v1 Announce Type: new Abstract: Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data generation and training, where a polic
arXiv:2610.25861v2 Announce Type: replace Abstract: Game world models have made rapid progress toward real-time interactive generation. Yet action control is still predominantly implemented as feature conditioning, leaving the model to learn from training data how each action sho