首页 / 浏览
浏览全部已收录的公开内容，包括尚未归入主分类的条目。
7948 条公开内容
V2EX ·
Zooproxy ——全球领先的高性能代理服务平台 聚合超 1 亿真实 IP 资源，覆盖 195 + 国家和地区。每日动态更新 IP 池，确保节点纯净度与匿名性，为数据采集、跨境业务提供稳定可靠的网络桥梁。 三大核心 IP 服务 动态住宅 IP：$0.38 / GB ，不限 IP 数量 静态 ISP 独享 IP：$0.9 / IP ，不限流量 端口无限套餐：$0.38 / 端口 / 天，无限流量，不限 IP ✅ 免费测试：提供全功能试用资源，零门槛体验核心服务 ✅ 超值定价：行业标杆级性价比，新老用户专享限时折扣，高流量套餐享额外优惠 🎁200MB 动态住宅 IP 兑换码 ZRC9-8P6R-X4DE VF3T-EGAJ-M3XB LEX6-BHZ7-L7R5 TTPR-Z3ZN-UWXZ 7PB2-RCY7-LGVQ 复制前往控制台 CDK 栏兑换，领不到的留言 👉 https://zooproxy.com/?kwd=zsy-v2ex
GitHub Issues ·
huggingface/transformers 仓库的第 50381 号公开问题报告，完整描述与讨论可在原始 Issue 查看。
V2EX ·
ChatGPT Plus 120 ChatGPT 5x 640 ChatGPT 20x 1100 +V = QVpJWklPT08=
V2EX ·
Lovableapp 是我花了一年做的导航站。 起因是，由于 vibe coding 的火热，vercel.app 或者 lovable.app 下有好多 vibe coding 的作品，能解决需求，有热度，但是找起来困难。 我就做了这个聚合站，最高的时候每个月 80w pv 。然后这时候，乐极生悲，谷歌 8 月下旬的 spam 更新，认定我的网站是垃圾内容，流量已下降几乎全没了，只剩下 30K 。 我试了好多，看看能不能挽回，增加新的工具等，都不行。 我刚刚加了 bid 模式 ，就是类似 outbid.lol 那种。 最后后的尝试，增加一些用户的活跃，看能不能好起来。 网站目前还有 30K 访问，DR>60 。
GitHub Issues ·
langchain-ai/langgraph 仓库的第 9602 号公开问题报告，完整描述与讨论可在原始 Issue 查看。
Hacker News ·
由 farmerbb 提交。Hacker News 最近记录 79 票、32 条评论，观测日期为 2026年11月5日（UTC）。
Hacker News ·
由 gmays 提交。Hacker News 最近记录 48 票、16 条评论，观测日期为 2026年11月5日（UTC）。
Hacker News ·
由 pr337h4m 提交。Hacker News 最近记录 2 票、0 条评论，观测日期为 2026年11月5日（UTC）。
GitHub Issues ·
huggingface/transformers 仓库的第 50378 号公开问题报告，完整描述与讨论可在原始 Issue 查看。
MIT News ·
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
arXiv ·
arXiv:2611.05390v1 Announce Type: new Abstract: Multi-agent language-model systems often add a reviewer to improve an upstream agent's decision. Yet a reviewer can both repair errors and replace decisions that were already correct. We study this as a problem of institutional jurisdiction: conditional on the same proposal, task information, model, and review output, when is the reviewer authorized to make its recommendation binding? We compare broad override authority with an evidence gate that p
arXiv ·
arXiv:2611.05391v1 Announce Type: new Abstract: Tool descriptions tell an agent what an action can do, but they do not necessarily reveal whether that action is healthy or suitable at the moment of use. Execution harnesses often possess this information through monitors, traces, and recent failures while the model choosing the next action does not. We call this gap operational blindness. We introduce Agent Harness Awareness, a trust-separated design in which the host supplies a small, fresh, ver
arXiv ·
arXiv:2611.05392v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) systems powered by large language models (LLMs) execute as autonomous multi-step pipelines that dynamically invoke tools, integrate observations into memory, and iterate until a task is resolved or a resource budget is exhausted. Unlike classical workflows with fixed graphs, the aggregate compute, bandwidth, and end-to-end latency demands of such pipelines are unknown at dispatch time: they emerge at runtime fro
arXiv ·
arXiv:2611.05393v1 Announce Type: new Abstract: Large language models perform strongly on standard medical QA but degrade on harder reasoning tasks, where multi-agent debate often fails to beat strong single-model prompting. We argue that a key limitation is that existing systems select experts and retrieve knowledge from the question alone, rather than from gaps that emerge during reasoning. We propose challenge-aware adaptive recruitment: an external CHALLENGER inspects the evolving reasoning
arXiv ·
arXiv:2611.05394v1 Announce Type: new Abstract: Tiered inference distributes large language model computation across a hierarchy of devices, from on-device and edge hardware to the datacenter, and is increasingly offered as the route to cheaper, lower-latency, and more private serving. Most such systems orchestrate frozen model checkpoints, and most decide what to resolve locally and what to escalate using a confidence signal produced by a forward-deployed model. We give a closed-form condition
arXiv ·
arXiv:2611.05450v1 Announce Type: new Abstract: As agents become more capable, they are moving beyond one-off tasks toward sustained assistance across successive user goals. Such assistance requires agents to discover how unfamiliar environments work, reuse what they learn across tasks, and keep that experience current as environments evolve. Existing benchmarks increasingly study experience reuse and adaptation, but provide limited insight into which parts of accumulated experience agents revis
arXiv ·
arXiv:2611.05459v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: finding relevant articles, interpreting them, synthesizing across them, and proposing future research. The benchmark is a published review of the Spanish plume weather pattern and its 102-article corpus. In the initial searche
arXiv ·
arXiv:2611.05512v1 Announce Type: new Abstract: AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects, where critical information is scattered across conversations, code, and evolving decisions. Even simple workplace questions may require loca
arXiv ·
arXiv:2611.05524v1 Announce Type: new Abstract: We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of per-agent and pairwise barrier sets; (ii) derive centralized and
arXiv ·
arXiv:2611.05542v1 Announce Type: new Abstract: Whole-page ranking jointly optimizes advertisements and organic content to balance business outcomes and user engagement under complex layout and business constraints. Existing non-autoregressive (NAR) approaches enable efficient page generation but typically score candidate items independently of previously selected items, limiting their ability to capture order-dependent interactions. Autoregressive (AR) methods address this limitation through se
arXiv ·
arXiv:2611.05548v1 Announce Type: new Abstract: We evaluate the extent to which agentic AI models can complete an end-to-end data science project, and how this improves with feedback. A 'writer' model with specific tools creates a complete data science project including downloading, cleaning, and analyzing a dataset, and writing a short paper about it. The project is executed and a 'grader' model evaluates it. The writer can then revise its submission, and this repeats for a total of three round
arXiv ·
arXiv:2611.05549v1 Announce Type: new Abstract: Transparency has become a central principle in AI governance, yet there is little agreement about what transparency means, for whom, and in what contexts. Drawing on interpretive flexibility within the Social Construction of Technology, this paper examines how different stakeholders understand and experience transparency in generative AI. This study draws from a global survey of 400 end-users, AI builders, and policymakers, complemented by a struct
arXiv ·
arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow. These decisions depend on local data representations and operational conventions and can involve source selection, patient and encounter identity, l
arXiv ·
arXiv:2611.05556v1 Announce Type: new Abstract: LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer. In this regime the per-item mean weights weak judges as heavily as strong ones, and confusion-table models such as Dawid-Skene must estimate a per-judge error table
arXiv ·
arXiv:2611.05581v1 Announce Type: new Abstract: Real-world vision is dynamic and scene-rich, while EEG and fMRI resolve it at complementary temporal and spatial scales. Most neural decoding systems, however, align one modality in isolation and mostly against static images or short clips. We study the synchronized case: EEG and fMRI are recorded during the same long-form naturalistic viewing, giving a shared stimulus but also recurring narrative context and many semantically similar candidates. W
arXiv ·
arXiv:2611.05586v1 Announce Type: new Abstract: As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge. Existing reputation systems depend on scarce resources like human curation, identity credentials, or voluntary reviews, while naive volume rankings are vulnerable to Sybil attacks. We evaluate whether existing onchain payment histories can yield provider ratings that are resilient against Sybil attacks. Using a 157-day dataset com
arXiv ·
arXiv:2611.05590v1 Announce Type: new Abstract: What should ``verified'' mean when evaluating LLM-generated code? Many existing pipelines report a single verification number. We argue this collapses three distinct properties measured in a conditional audit sequence: verifier acceptance (Surface A), \emph{syntactic specification binding (Surface B: does the proof obligation bind to the spec?), and \emph{semantic specification fidelity} (Surface C: does the spec capture the informal requirement?).
arXiv ·
arXiv:2611.05611v1 Announce Type: new Abstract: Speculative decoding (SD) speeds up large language model (LLM) serving, but its gain depends on the workload's \emph{shape}, such as batch size and context length, and on its \emph{content}. A model-based drafter proposes a short block on any content, while a model-free drafter such as n-gram lookup proposes long copies at almost no cost when the output repeats its input, as in code editing. Adaptive verification spends a batch-wide verification bu
arXiv ·
arXiv:2611.05620v1 Announce Type: new Abstract: On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are near saturation. We introduce ViBench 2.0, a benchmark for long-horizon software building that we use to select our platform's models. Its 17 full-stack web products, modeled on widely used software, grow over 241 featur
arXiv ·
arXiv:2611.05632v1 Announce Type: new Abstract: Autonomous software agents can act through tools, delegate work, and change their models or execution environments while earlier authorizations remain in flight. We present Assurance-Conditioned Continuous Authorization (ACCA), an approach designed to be harness-independent, for maintaining operational authority according to currently justified assurance. It distinguishes evidence validity from contextual applicability, derives assurance claims fro