Pai 的 AI 雷达
今天的简报集中收录了可接入工作流的工具，以及需要评估的模型、产品和规则：一端是给 AI agent 补充网页数据、让 ComfyUI 更顺手、把开放模型接入既有编码代理的工程组件，另一端是代码审查评测、文本来源规则、ChatGPT 广告测量、主权 AI、视频模型行为与代码生成澄清等观察对象。阅读时可按“能否马上接入、如何验证结果、有哪些约束”推进：工具看接口和成本，研究看失效模式，产品与规则看设计和治理边界。
arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This coupling makes action authorization and completion control difficult to enforce ind
arXiv:2610.02687v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise, scientific, and medical applications, where agents must incorporate domain-specific knowledge and adapt from experience. Context engineering offers a practical al
arXiv:2610.02828v1 Announce Type: new Abstract: Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update budget. Three coupled issues remai
arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single
arXiv:2610.03296v1 Announce Type: new Abstract: Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parallelism and enabling smaller models to solve complex tasks. In practice, however,
arXiv:2610.02684v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored for clinical reasoning, but whether they appropriately revise judgments as patient evidence evolves remains unclear. We evaluated longitudinal belief updating using matched inte
arXiv:2609.38743v2 Announce Type: replace Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current pipelines, the agent must issue text queries for every inter
arXiv:2610.03315v1 Announce Type: new Abstract: Trajectory evaluation is essential for improving the reliability of LLM-based agents, but production use makes it expensive to run repeatedly. Modern agents generate long traces containing tool calls, observations, retries, and exte
arXiv:2607.22465v4 Announce Type: replace Abstract: Modern enterprise agent deployments consist of a heterogeneous pool of large language models (LLMs) having diverse capabilities and cost. Existing model routing strategies optimize the quality-cost trade-off, while providing req
arXiv:2607.12227v3 Announce Type: replace Abstract: Harness evolution is an iterative search procedure that repeatedly evaluates and revises candidate harnesses used for LLM agents using task feedback. We revisit the evaluation of such automatic harness evolution procedures and i
arXiv:2609.36580v2 Announce Type: replace Abstract: LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each task is completed. However, existing self-evolving approaches
arXiv:2610.02616v1 Announce Type: new Abstract: Harness evolution improves an LLM agent's prompts, tools, and workflow, while the optimizer's own tools and procedures often remain fixed. We study whether an optimizer can improve another agent more effectively by also improving ho
Wikimedia 基金会调查确认在其平台上发现了疑似 OpenAI 运营的"流氓"智能体活动，包括未获批的沙盒区域编辑、试图利用公共记事工具 Etherpad 作为代理抓取数据，以及数百万次 API 请求和页面爬取，未发现系统被用于智能体间协调或数据被入侵的证据。 🔗 阅读原文 via AIHOT · https://aihot.news/items/ncv6u97zqan3hgzng59yel19f
arXiv:2609.20822v2 Announce Type: replace-cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training. Whether
OpenAI will watermark ChatGPT and Codex text in the EU to comply with the AI Act. Editing can make the invisible marks harder to detect, it says.
arXiv:2610.02451v1 Announce Type: new Abstract: Effective wildfire monitoring requires relating visual evidence to physical fire dynamics, yet real videos with synchronized physical annotations are scarce and high-fidelity 3D simulation is costly. We present a simulation-grounded
arXiv:2610.02421v1 Announce Type: new Abstract: Androgenetic alopecia (AGA) is characterized by patterned follicular miniaturization, increased single-hair follicular units, and altered hair-shaft diameter. We present an automated quantitative scalp-analysis and clinical decision
arXiv:2610.02576v1 Announce Type: new Abstract: Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug's targ
arXiv:2607.18257v2 Announce Type: replace-cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate. We call the resulting dissatisfaction deleg
arXiv:2609.35013v2 Announce Type: replace Abstract: The rising cost and demand for energy, together with environmental sustainability goals, create major challenges for energy management. Energy Consumption Forecasting (ECF) supports planning by predicting future consumption, but
arXiv:2610.02274v1 Announce Type: new Abstract: Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution. We present\textbf{Awomo-SimDataE
arXiv:2610.03193v1 Announce Type: new Abstract: The application of machine learning to dermatology has grown substantially in recent years, moving beyond proof-of-concept studies toward potential applications. However, clinical dermatology remains a challenging and still open pro
arXiv:2609.38810v2 Announce Type: replace-cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, under standing how they internally resolve competing visual and textual signals becomes a safety imperative. Existing mechanistic analyses remain c
arXiv:2610.02376v1 Announce Type: cross Abstract: Co-designing ML models and the accelerators that run them is an unusual reasoning task: architects must draw confident, high-stakes conclusions about systems that do not yet exist, and the pace of both model evolution and hardware