Aggregate arXiv cs.AI 人工智能 45″

Adaptive Hybrid Particle Swarm Optimization with Gradient Descent

arXiv:2608.…

• 11258v1 Announce Type: new Abstract: Gradient injection helps Particle…
• We propose Adaptive Hybrid PSO (AHPSO), which uses a sigmoid function …
• Under budget-normalized comparison (PSO given equivalent total functio…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures

arXiv:2608.…

• 11255v1 Announce Type: new Abstract: Accurate prediction of vapor--liq…
• While deep learning models can provide accurate predictions, they ofte…
• In this work, we propose a symbolic machine learning approach to disco…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Local verification cannot detect non-transportability: a cohomological theory of context preservation in agentic reasoning

arXiv:2608.…

• 11252v1 Announce Type: new Abstract: Agentic AI systems routinely tran…
• We prove this class of safeguard is structurally incomplete.
• Modelling a covering of context space by its nerve and evidence by a r…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search

arXiv:2608.…

• 11250v1 Announce Type: new Abstract: Language models can propose many …
• We present AgonAlpha, an architecture that searches over frozen resear…
• To our knowledge, AgonAlpha is the first alpha-mining system to combin…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents

arXiv:2608.11248v1 Announce Type: new Abstract: Long-term memory is essential for language agents operating across extended interactions and evolving tasks.…

• Existing memory-augmented agents mainly focus on storing and retrievin…
• In particular, previously distilled insights can become outdated, over…
• To address this issue, we study insight-level memory maintenance for l…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier

arXiv:2608.…

• 11247v1 Announce Type: new Abstract: Recent advances in language model…
• Each agent sees what the others assert before it answers, so peer opin…
• We measure that displacement in 23 open-weight models, 19 conditions, …

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Towards the Harness of Embodied Agents

arXiv:2608.…

• 11246v1 Announce Type: new Abstract: The success of coding agents has …
• We ask whether the same paradigm extends to embodied agents in the phy…
• We present Thea, a harness in which an agentic loop orchestrates robot…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Model

arXiv:2608.11244v1 Announce Type: new Abstract: Construction standards are critical for building safety and sustainability.…

• Existing standard application workflows rely on keyword-based document…
• To address these limitations, this study develops a multimodal knowled…
• The framework introduces 1) a multimodal knowledge graph (MKG) for uni…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Towards Sustainable Learning in Online Education: A Reinforcement Learning Approach

arXiv:2608.…

• 11245v1 Announce Type: new Abstract: Online education offers unprecede…
• To address these challenges, we introduce AI Tutor, a reinforcement le…
• In the short term, AI-Tutor draws on cognitive theory to guide learner…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification

arXiv:2608.…

• 11243v1 Announce Type: new Abstract: We argue that a single structural…
• , the agent does not escape its sandbox) is an off-support object.
• Formally, if q is the data distribution and \(p(\cdot\mid w)\) the mod…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle

arXiv:2608.…

• 11241v1 Announce Type: new Abstract: Deploying LLM agents into industr…
• Any two can be maximized against the third.
• We present RecSys Factory, an LLM-agent platform deployed for 78 days …

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

VQ-bench: A Composable Vector Quantization Framework

arXiv:2608.11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure.…

• It is therefore experiencing a surge of renewed engineering and resear…
• This paper provides a unified framework for developing and benchmarkin…
• We describe 7 common conceptual quantization primitives and show how t…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability

arXiv:2608.…

• 11238v1 Announce Type: new Abstract: Retrieval-augmented generation im…
• We propose Q-CARE, a query-agnostic and fully reference-free framework…
• Q-CARE establishes a unified evaluation principle based on query cover…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

arXiv:2608.11235v1 Announce Type: new Abstract: Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon.…

• Many predictions stabilize early, but blockwise decoding continues unt…
• Existing accelerators often rely on learned filters, modified scores, …
• We ask whether native trajectory signals can identify residual positio…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction

arXiv:2608.11237v1 Announce Type: new Abstract: Neural operators have shown strong potential for learning solution operators of partial differential equations (PDEs).…

• However, long-horizon autoregressive prediction remains challenging: l…
• Existing methods mainly improve state representations and operator bac…
• To address these issues, we propose a geometry-aware incremental neura…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

InfraBench: Evaluating Infrastructure Agents Across Layers, Lifecycle, and Risk

arXiv:2608.11234v1 Announce Type: new Abstract: Managing modern computing infrastructure has become a steadily harder problem due to the ever-increasing complexity.…

• Recent advances in AI agents create a timely opportunity to automate i…
• We present InfraBench, a benchmark suite for evaluating AI agents on r…
• Experiments with 15 agent-model configurations show that even the stro…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs

arXiv:2608.11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).…

• Existing PIC methods, however, are built for full-attention models, wh…
• Hybrid LLMs break these primitives---they replace most attention layer…
• This raises a natural question: can PIC benefit hybrid models, and wha…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

The Edge-based Contiguous p-median Problem with Connections to Logistics Districting

arXiv:2608.…

• 11230v1 Announce Type: new Abstract: This paper introduces the edge-ba…
• Two binary programming models are introduced, both of which incorporat…
• The first model requires an exponential number of cut set-based constr…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Forecasting Side Effects of Activation Steering

arXiv:2608.…

• 11227v1 Announce Type: new Abstract: Activation steering modifies a la…
• While effective, steering often produces unintended side effects on ot…
• We therefore ask: can these side effects be forecasted before steering…

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate arXiv cs.AI 人工智能 45″

Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version)

arXiv:2608.…

• 11229v1 Announce Type: new Abstract: Comparative feedback, asking peop…
• Preference-based reward learning typically casts the human teacher as …
• We argue this forfeits the teacher's defining advantage: knowledge of …

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate 极客公园 人工智能 45″

打破机器人「数据焦虑」，穹彻智能想建一条「训练数据」生产线

如果说 2025 年是具身智能爆发的一年，那么今年，行业竞争已经开始进入新的阶段。从国内外越来越多机器人公司发布新产品，到资本持续加码，具身智能正成为 AI 领域最受关注的方向之一。…

• 但随着行业快速发展，一个新的共识正在形成：真正限制机器人进化速度的，不再只是模型，而是数据。
• 与大语言模型可以利用互联网海量文本不同，机器人需要学习的是现实世界中的操作能力。
• 一次抓取、一段搬运、一场整理任务，都需要真实发生，并同步记录视觉、动作、轨迹等多模态信息。

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate 极客公园 人工智能 45″

AI Agent 手机下半场，「国标」L3 只是起点

一张证书，暂时还不会影响到你「换机」节奏。作者｜张勇毅 编辑｜靖宇 时间回到 7 月下旬，如果你关注智能手机领域的话，应该会记得大量手机厂商开始官宣自己的手机，通过了国家人工智能 L3 级认证。…

• 这轮集体官宣的起点，是 2026 年 7 月 17 日公布的首批人工智能终端智能化分级测试结果。
• 按照首批测试名单，移动终端中共有 11 款产品达到 L3，包括 9 部手机和 2 台平板。
• 手机部分覆盖华为、摩托罗拉、荣耀、vivo、OPPO、小米和阶跃星辰等品牌。

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate 极客公园 人工智能 45″

DeepSeek 的「斩杀线」，正在重塑 AI 行业的世界观

作者｜Techno 之王 编辑｜靖宇 8 月 4 日，「DeepSeek 斩杀线」竟然冲上微博热搜。V4 Flash 正式版凭借极致的性价比，在全球 AI 大模型的「成本-性能」坐标系上划出了一条残酷的行业生死线——比它贵的没它强，比它弱的没它便宜。…

• 开发者社区群情振奋，甚至外溢成了更大人群津津乐道的话题。
• 当看起来 AI 世界的定价权已经易手，所有人为极致性价比欢呼的时候，两天后，8 月 6 日，DeepSeek 在开放平台后台发布了一条简短的…
• 」 刚被行业定义为画出「斩杀线」的那只手，为何转头就签了涨价通知。

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后

Aggregate 极客公园 人工智能 45″

Fitbit Air 手环深度体验：「无屏」只是手段，模型能力才是护城河

无屏只是形态，模型才决定产品的上限。作者｜张勇毅 编辑｜靖宇 如果你问我：今年最火的 AI 硬件是什么？这个问题大概会有很多答案。但如果你问的问题收束成：「今年最火的 AI 可穿戴硬件是什么？…

• 」那答案大概率只有一个—— Fitbit Air。
• 仅仅一个数据就足以说明它的现象级爆火：作为一款官方开售已经超过两个月的设备，在二手平台你至今仍然需要加价 200~300 元购买。
• 作为从去年开始就苦苦寻找取代传统智能手表形态产品的健康监测设备的我，也是拜托朋友第一时间买到了这款无屏手环。

RSS 官方收录 · 可信分层展示

详情 原文 分享图 复制摘要 稍后