微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接后用系统浏览器访问。
XMT
信流 · 上滑连读 · 来源可核
Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling
arXiv:2608.…
- 26199v1 Announce Type: new Abstract: We ask whether AI agents powered …
- In these environments, engineers issue repetitive, dependency-ordered …
- Confidentiality constraints on component specifications and naming con…
RSS 官方收录 · 可信分层展示
Agentic AI for operating scientific instruments for nanoscale characterization
arXiv:2608.26198v1 Announce Type: new Abstract: Operating a scientific instrument such as an atomic force microscope (AFM) requires continuous expert decision-making.…
- A trained user defines the experimental intent, translates it into ins…
- Existing automation usually addresses only parts of this workflow thro…
- Here we present an agentic-AI framework that operates the executable p…
RSS 官方收录 · 可信分层展示
AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes
arXiv:2608.…
- 26193v1 Announce Type: new Abstract: Multimodal large language models …
- Models may predict correct answers while neglecting people-centric cue…
- Prior reinforcement learning approaches mainly reward context or logic…
RSS 官方收录 · 可信分层展示
Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs
arXiv:2608.…
- 26191v1 Announce Type: new Abstract: Incident risk prediction from lon…
- We propose structured evidence routing, a router-predictor-reviewer wo…
- The router organizes the complete pre-index EHR into a compact summary…
RSS 官方收录 · 可信分层展示
Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
arXiv:2608.…
- 26190v1 Announce Type: new Abstract: World models enable agents to rea…
- In this work, we propose a compatibility prediction Latent World Model…
- Our key insight is that spatial proximity correlates with latent featu…
RSS 官方收录 · 可信分层展示
Dunamu and Visa partner on stablecoin, AI business; Open Standard’s OUSD under consideration
Dunamu and Visa partner on stablecoin, AI business; Open Standard’s OUSD under consideration
- Dunamu and Visa partner on stablecoin, AI business; Open Standard’s OUSD under consideration
RSS 官方收录 · 可信分层展示
Climate Change Exposes 580 Million Children to 20 Extra “Heat-Stress Days” Every Year
By Ayesha Tandon More than 40% of children under the age of 10 globally are already experiencing at least 20 additional “heat-stress days” due to climate change.…
- This is according to a new attribution study, published in Science Adv…
- [continued] The post Climate Change Exposes 580 Million Children to 20…
RSS 官方收录 · 可信分层展示
Invocation-Level Reliability of Tool-Using Agents
arXiv:2608.…
- 26189v1 Announce Type: new Abstract: Tool-using agents fail two ways: …
- We measure a correct-invocation rate that separates the two, under bot…
- By depth 6, roughly 70% of a model's own clean-context capability is l…
RSS 官方收录 · 可信分层展示
Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion
arXiv:2608.…
- 26185v1 Announce Type: new Abstract: Equal participation in co-located…
- We present SecondVoice, a mixed-reality system that enables people to …
- By separating what is said from who says it, SecondVoice brings hesita…
RSS 官方收录 · 可信分层展示
Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments
arXiv:2608.26188v1 Announce Type: new Abstract: Large language models are increasingly used to inform safety decisions in cities, such as where it is safe to walk, rent, or travel.…
- We ask whether such judgments track measured risk or the patterns atta…
- We probe seven instruct-tuned models under three conditions that disso…
- First, ratings are nearly flat under coordinates for six of seven mode…
RSS 官方收录 · 可信分层展示
TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education
arXiv:2608.…
- 26184v1 Announce Type: new Abstract: AI programming tutors provide sca…
- We present TutorTrace, a dataset and behavioral abstraction pipeline t…
- Across four deployments in two introductory Python courses (N=480), Tu…
RSS 官方收录 · 可信分层展示
Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI
arXiv:2608.…
- 26182v1 Announce Type: new Abstract: Large language models (LLMs) are …
- As a result, robots may present hallucinated capabilities, unclear beh…
- This paper develops a framework for prompt design in LLM-based robots …
RSS 官方收录 · 可信分层展示
Factcheck: 10 Flaws in the Conservative Report on “Cheap Power”
By Josh Gabbatiss, Molly Lempriere, Simon Evans In a new report, the opposition Conservatives argue that UK electricity prices are too high and that it would be better for the climate to have cheap electricity, even if that means using more gas.…
- The idea is that cheap power would encourage people to use .
- [continued] The post Factcheck: 10 Flaws in the Conservative Report on…
RSS 官方收录 · 可信分层展示
世界模型进入下半场：自变量 WALL-SS 突破三大瓶颈，让虚拟世界成为机器人的「训练场」
机器人世界模型的下一场竞争，可能不是画质，是架构。作者｜Li Yuan 编辑｜郑玄 一只机械臂的夹爪明明没有夹住杯子，杯子却像被磁铁吸住一样，跟着夹爪升了起来。这个看似荒诞的问题，正在困扰机器人世界模型，业内甚至将其称为「磁铁式抓取」。…
- 视频生成模型只要让画面看起来合理，就算完成任务；但世界模型不能只追求「像真的」。
- 机器人训练数据大多来自成功演示，模型容易形成捷径：与其理解动作的细微差别，不如按照画面，直接生成最可能的结果。
- 可在真实世界里，夹爪位置偏移几毫米，就可能让结果从抓起变成碰倒杯子甚至抓空。
RSS 官方收录 · 可信分层展示