ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL

arXiv:2608.…

• 27796v1 Announce Type: new Abstract: Recent work has shown that reinfo…
• However, most existing approaches treat SQL generation as a single-tur…
• We present ReToolSQL, a two-stage training framework for text-to-SQL t…

RSS 官方收录 · 可信分层展示

Credo: Reusable Declarative Primitives for Agentic Workflows

arXiv:2608.…

• 27790v1 Announce Type: new Abstract: An LLM application depends on bot…
• Coding agents can now discover strong harnesses by searching over cand…
• The potential for reuse, however, is substantial.

RSS 官方收录 · 可信分层展示

Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models

arXiv:2608.…

• 27768v1 Announce Type: new Abstract: A language model with access to t…
• We separate this failure into two precisely defined quantities: occurr…
• On one fixed Qwen3-32B setup, 33 of 512 first responses to 256 new pro…

RSS 官方收录 · 可信分层展示

Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls

arXiv:2608.27727v1 Announce Type: new Abstract: A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.…

• the distribution over stimuli it implicitly expects.
• Interpretability research has traditionally studied models by holding …
• Neither reconstructs the prior distribution itself, since internal str…

RSS 官方收录 · 可信分层展示

PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation

arXiv:2608.…

• 27716v1 Announce Type: new Abstract: AI systems are being deployed on …
• One such workflow is estimating a product carbon footprint (PCF), the …
• AI agents are increasingly being used to generate PCFs, but existing e…

RSS 官方收录 · 可信分层展示

旺季大促即将开启，沃尔玛全球电商旺季峰会释放了哪些海外全渠道增长信号？

在旺季大促即将来临之际，8月13日，沃尔玛全球电商旺季峰会在深圳圆满落幕！围绕“全渠道领航，高质量立信”，沃尔玛全球高层与中国卖家们齐聚现场，共话旺季市场新机遇与战略规划。本次峰会创参会人数历史新高，现场卖家们踊跃参与、积极互动，入驻意愿强烈！…

• 如何把今年做成最好的一年？
• 这几乎是所有卖家们的心声。
• 最好的旺季显然不是一蹴而就，而是需要从现在开始就打下关键基础：以顾客需求决定商品，以全渠道能力扩大触点，再让库存、履约与广告在流量高峰前协同…

RSS 官方收录 · 可信分层展示

定义物理 AI 新纪元：昂首 EV1 智能出行机器人落地深圳湾 INNO100，开启中国市场线下首发

2026 年 8 月 29 日，全球领先的物理 AI 与机器人创新企业若创科技（昂首 Strutt）于深圳湾 INNO100 全球创新旗舰店正式举行中国线下首发仪式，展示旗下旗舰产品——昂首 EV1 智能出行机器人。…

• 作为累计完成近亿美元融资的硬科技领军者，昂首 Strutt 以前瞻性的个人移动体验为切入点，正加速推动“物理 AI”技术走向消费级规模化应用。
• 以端到端架构，重构个人移动体验 雷峰网了解到，昂首团队拒绝将个人出行设备降维定义为传统的辅助代步工具，而是将其打造为集“感知、决策、控制与动…
• • 双核心工程架构： EV1 深度融合了自研的伴行智驾系统与凌波底盘系统。

RSS 官方收录 · 可信分层展示

Agents for Everyone: A Workshop Framework for Building Agentic AI Capabilities in a Distributed Curation Community

arXiv:2608.27675v1 Announce Type: new Abstract: Agentic AI has the potential to accelerate curation of biological databases and knowledge bases.…

• However, uptake has been hindered by a number of challenges and obstac…
• Here we describe how we have attempted to address and mitigate these c…
• Our cloud environment for agentic-assisted curation was based on the J…

RSS 官方收录 · 可信分层展示

A Framework for Object-Centric Predictive Monitoring of Collaborative Processes

arXiv:2608.…

• 27671v1 Announce Type: new Abstract: Predictive Process Monitoring (PP…
• Existing approaches extend traditional event logs with collaboration a…
• Object-centric process mining (OCPM) provides an alternative by repres…

RSS 官方收录 · 可信分层展示

If Agents Were Angels, No Governance Would Be Necessary: Out-of-Band Policy Enforcement at a Trusted Tool Boundary

arXiv:2608.27646v1 Announce Type: new Abstract: Give an agent a human's credential and it inherits the person's reach without the judgment that limits its use.…

• It can sweep every reachable record into model context, where hidden i…
• Prompts are a brittle guardrail: one fallible reasoner interprets the …
• We present Out-of-Band Policy Enforcement (OBPE), a trusted boundary o…

RSS 官方收录 · 可信分层展示

Generative AI Expands the Intellectual Reach of Course Based Undergraduate Research Experiences (CUREs)

arXiv:2608.…

• 27638v1 Announce Type: new Abstract: Course-based undergraduate resear…
• Generative artificial intelligence (GenAI) may extend this support by …
• However, how embedding GenAI within a CURE to provide support across t…

RSS 官方收录 · 可信分层展示

LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails

arXiv:2608.…

• 27580v1 Announce Type: new Abstract: Safety guardrails serve as the la…
• We present LongGuard, a framework that evaluates, mechanistically anal…
• We formulate the task as Safety Needle-in-a-Haystack (SafetyNIAH) over…

RSS 官方收录 · 可信分层展示

独家丨叠风新能源完成数千万战略融资，发力船舶风力辅助推进赛道

雷峰网独家获悉，国内船舶风力辅助推进系统（WAPS）企业叠风新能源（DEALFENG®）已于近期完成数千万战略轮融资，本轮由产业投资方海德威集团出资。叠风新能源聚焦船舶风力辅助推进赛道，是国内最早拿到旋筒风帆多国船级社认证、实现量产商业化落地的企业。…

• 创始人李智拥有深厚船舶设备行业经验，主导完成国内首个中国船级社的旋筒风机型式认可以及多国船级社 AiP 认证；核心团队汇聚航空航天、船舶设计…
• 依托马格努斯效应原理，叠风新能源的核心产品旋筒风帆依靠旋转圆柱体捕获风能，为船舶提供辅助推力。
• 对比海外同类竞品，产品价格仅约海外竞品的 60%，可以有效缩短船东的投资回报周期。

RSS 官方收录 · 可信分层展示

Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator

arXiv:2608.…

• 27548v1 Announce Type: new Abstract: Safety moderation for deployed AI…
• Existing guardrails usually cover only part of this setting, making it…
• We present Nemotron 3.

RSS 官方收录 · 可信分层展示

SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coaching

arXiv:2608.27524v1 Announce Type: new Abstract: Corporate training teams need scalable and explainable tools to improve workforce communication in multilingual settings.…

• Existing systems often score text, audio, or video in isolation, or pr…
• This paper presents SETU, an agentic ecosystem for corporate communica…
• SETU is designed for two scoped scenarios: (i) recruiter-candidate eli…

RSS 官方收录 · 可信分层展示

Thinking Costs Tokens: When More Structure is Worth the Price

arXiv:2608.…

• 27506v1 Announce Type: new Abstract: Adding inference structure to a l…
• In this paper, we investigate whether there exists a token-budget thre…
• We evaluate two systems on FinQA and TAT-QA financial reasoning tasks,…

RSS 官方收录 · 可信分层展示

WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learning

arXiv:2608.27508v1 Announce Type: new Abstract: GUI agents trained with reinforcement learning (RL) have showcased strong environment learning capabilities on mobile platforms.…

• However, RL typically demands extensive real-environment interactions,…
• To address these, we propose WM-R1, the first reinforcement learning f…
• Specifically, world models serve as the source of state transitions du…

RSS 官方收录 · 可信分层展示

CareGraph: An Auditable Hybrid AI Framework for Evidence-Grounded Personalized Longitudinal Health Intelligence

arXiv:2608.…

• 27484v1 Announce Type: new Abstract: Artificial intelligence is transf…
• We present CareGraph, an auditable hybrid AI framework that converts h…
• CareGraph organizes evidence without diagnosing, predicting outcomes, …

RSS 官方收录 · 可信分层展示

Netflix采用云原生作业队列系统Kueue替代内部解决方案

点击查看原文>

RSS 官方收录 · 可信分层展示

极米海外众筹被叫停背后：AI 眼镜的「撞脸」之战，谁能留到最后？

从朋友圈骂战到美国法院，极米和逸文的三年恩怨。作者丨黄艳冰 编辑丨姚单 董子博8 月 27 日，本应是 MemoMind One 众筹顺利收官的日子。但就在收官前最后一晚，MemoMind One 项目突然被 Kickstarter 暂停，页面显示为"涉及知识产权争议，目前无法使用”。…

• 不少支持者收到 Kickstarter 平台邮件，显示原本支付的支持金额将自动退回，不会产生扣款。
• MemoMind One 是投影厂商极米科技旗下 AI 眼镜项目的首款产品。
• 此前，这款眼镜已经在 Kickstarter 上筹得超过 120 万美元，吸引了 2000 多名支持者。

RSS 官方收录 · 可信分层展示

Context Localization for Generalized Level-Based Evaluation in Knowledge-Based Systems

arXiv:2608.27482v1 Announce Type: new Abstract: We study context localization for generalized level-based evaluation in knowledge-based systems.…

• The framework models situations where a structured nonnegative score, …
• The generalized level measure maximizes a monotone set function over a…
• We characterize when filtering the score by a context $B$ is equivalen…

RSS 官方收录 · 可信分层展示

Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations

arXiv:2608.…

• 27480v1 Announce Type: new Abstract: Tea plantations are vulnerable to…
• This study proposes an IoT-enabled acoustic monitoring framework integ…
• Research Method: Audio signals were captured non-invasively from tea t…

RSS 官方收录 · 可信分层展示

Benchmarking General Mobile Assistants in Challenging Real-World Scenarios

arXiv:2608.…

• 27477v1 Announce Type: new Abstract: Graphical user interfaces have em…
• Existing benchmarks such as AndroidWorld and MobileWorld provide stron…
• We present GMA, a benchmark for evaluating general mobile assistants i…

RSS 官方收录 · 可信分层展示

Class-Based Heuristic Selection for Solving the Flying Block Puzzle

arXiv:2608.…

• 27476v1 Announce Type: new Abstract: Heuristic search underlies planni…
• We study this problem through the two-column Flying Block Puzzle, a ri…
• We introduce the Class-Based Heuristic A* (CBHA*) algorithm, which int…

RSS 官方收录 · 可信分层展示