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。
9972 条公开内容
V2EX ·
好奇有无老板 team lead 真的这么做。 我工作上觉得很划水、逻辑不好的 PM ，我就让 AI 去读他在公司的轨迹，Slack 上的发言，Linear 上建的卡跟留言，让 AI 看看他有无闭环，有无乱搞，是在搞笑还是真的有在决策推进。不过也有些我拿不到上下文的地方，例如 Teams 上的会议。可能他只是对内部水，对客户可能很牛。 另外最近用公司提供的 AI 订阅有点心虚，老板要是让 AI 分析所有人的聊天，就能看到谁是有参与 AI 需求规划过程，谁是直接扔卡片给 AI 然后每个决策都是用 AI 推荐的那个。然后再分析产出每个人的产出以及对生产环境的影响。最后发现，直接扔卡的人表现更优 ：）
V2EX ·
如题，没用过中转站（也不想用）几个月前账号被标记封号后就再也没登陆成功过了，我看已经有人 买 mac mini 放到美国，然后远程登陆使用的案例了，直接线下操作实属硬核 大神们都有什么法子么
V2EX ·
前阵子跟孩子一起玩魔方，才发现自己已经忘得差不多了😂 以前好歹能分层法还原三阶，现在只会还原第一层，第二层的棱块怎么弄完全忘了，更别提第三层了。 本来想找个教程重新学学，后来想想，现在都 AI Coding 了，干脆自己写个工具试试，于是花了些时间 Vibe 了一个小程序。 用法就是把魔方六个面分别拍下来，识别颜色，然后计算出还原步骤，跟着 3D 动画一步步转就行。识别不准的颜色也可以手动改。拍照识别这块比想象中麻烦不少，光线、反光、角度都会影响结果，中间改了很多版。求解部分用的是 cubejs 的两阶段算法。 现在既有直接计算步骤的快速还原法，也有适合新手学习的分层还原法，可以按自己的需求选。 目前主要支持三阶魔方，功能还比较简单，肯定也有不少没考虑到的情况。 微信小程序叫「 CubeSnap 拍一拍还原魔方」，下面放个码。 有类似需求或者想学魔方的 V 友可以试试。如果遇到识别不准、操作不顺手之类的问题，欢迎反馈，我再慢慢优化。
GitHub Issues ·
huggingface/transformers 仓库的第 49902 号公开问题报告，完整描述与讨论可在原始 Issue 查看。
TechCrunch ·
Oura alleges in its newest lawsuit that Ultrahuman's Ring Pro infringes two of its patents.
Product Hunt ·
Documents of the future, made by AI, read by your team
Product Hunt ·
Live rankings of the tools AI agents use most
MIT News ·
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
TechCrunch ·
The company plans to begin testing Pony.ai's robotaxis in Kazakhstan's capital in the first half of 2027.
arXiv ·
arXiv:2610.30151v1 Announce Type: new Abstract: Every interaction between AI agents begins with a handshake: the initiating agent must locate its counterpart, learn what it can do, and establish a session before the first useful message can be sent. Surveys of agent communication protocols name handshake overhead as an efficiency criterion, yet none report measurements. This paper presents the first empirical, phase-decomposed benchmark of the handshake in three major agent protocols: MCP (in bo
arXiv ·
arXiv:2610.30157v1 Announce Type: new Abstract: AI agents require interfaces to interact with external systems such as files, APIs, databases, and cloud services. Two competing paradigms have emerged: CLI (Command Line Interface), where agents execute shell commands directly, and MCP (Model Context Protocol), a structured JSON-RPC protocol providing governed, typed tool access. This paper presents a comparative analysis across 14 evaluation dimensions, supported by worked examples, security asse
arXiv ·
arXiv:2610.30170v1 Announce Type: new Abstract: Canada's increasing wildfire activity requires frequent national hazard mapping to guide proactive mitigation, including fuel management, land-use planning, infrastructure protection, and evacuation routing. However, process-based wildfire simulation frameworks (e.g., BurnP3 and BurnP3+) rely on computationally intensive Monte Carlo simulations to model burn probability, fire intensity, and rate of spread. These workflows can take days to weeks to
arXiv ·
arXiv:2610.30173v1 Announce Type: new Abstract: Yager's 1987 rule of combination $\boxplus$ was proposed on epistemic grounds: under high conflict, mass should be redistributed to ignorance rather than renormalised onto the class simplex. We observe that backpropagation needs the same rule: Dempster's normaliser $(1{-}\kappa)^{-1}$, where $\kappa$ is the conflict mass, puts a $(1{-}\kappa)^{-2}$ term in the gradient that diverges exactly when evidence sources disagree, while Yager's $\boxplus$ i
arXiv ·
arXiv:2610.30176v1 Announce Type: new Abstract: We investigate structural conditions under which preferred and stable semantics agree in abstract argumentation frameworks. Our approach is based on suitably chosen sets of paths in the attack graph and binary relations induced by them. We establish a general path-based criterion for semantic agreement and instantiate it with several classes of paths, obtaining sufficient conditions expressed in terms of well-foundedness of the corresponding relati
arXiv ·
arXiv:2610.30205v1 Announce Type: new Abstract: When an LLM agent's move fails, the harness writes the move and the failure message into the transcript and asks again. In tool calling, this record makes small models more likely to repeat the failed action. We test whether the same holds in games (Sokoban, Connect Four, Othello), where a move can fail by being illegal or by being legal but losing, both verified exactly. On fixed probe items built by perturbing a correct move, the record backfires
arXiv ·
arXiv:2610.30277v1 Announce Type: new Abstract: While artificial intelligence has made rapid progress in mathematical reasoning, many open problems depend on structure that is revealed only through large-scale computational exploration and analytical synthesis. One such example is Lehmer's problem from 1933. It asks whether the Mahler measure of an integer polynomial, which measures how far its roots stray from the unit circle, can be made arbitrarily small. Previously, constructing irreducible
arXiv ·
arXiv:2610.30351v1 Announce Type: new Abstract: Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generate (Rouge), a hierarchical training framework that enables LLMs to adaptively decide when and how much reasoning is required for each input. Our approach decouples reasoning effort allocation from answer generation by introducing a routing policy that allocates a fixed sampling bu
arXiv ·
arXiv:2610.30391v1 Announce Type: new Abstract: Neuro-symbolic (NeSy) predictors that supervise only the task label suffer from reasoning shortcuts: distinct concept mappings achieve the same maximum likelihood, leaving the recovered concepts unidentifiable and unsafe for downstream reuse. We attack this failure by injecting a soft ontology prior over the latent concepts into the training objective and compiling it together with the task constraint into a smooth, decomposable probabilistic circu
arXiv ·
arXiv:2610.30429v1 Announce Type: new Abstract: Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable dynamic orchestration, trajectory-level rewards they apply assign one outcome to each decision, ofen struggling to identify the contributions of individual structural changes. We propose RoleFlow, a self-evolving multi-role agentic system that refines col
arXiv ·
arXiv:2610.30436v1 Announce Type: new Abstract: Sixth-generation (6G) communication systems are expected to support immersive, intent-driven, and latency-critical services through tight integration of multimodal intelligence, edge computing, and autonomous network control. In this setting, agentic AI systems can reason over heterogeneous inputs, use tools and network functions, coordinate across distributed entities, and adapt to dynamic environments. These capabilities make agentic multimodal i
arXiv ·
arXiv:2610.30443v1 Announce Type: new Abstract: Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across complex, temporally extended tasks with diverse inter-agent coordination requirements. We introduce a specification language that combines temporal-logic task specifications with operators for expressing such requirements. We propose SpecMAGIC, a hierarchical
arXiv ·
arXiv:2610.30445v1 Announce Type: new Abstract: AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight. Existing Human-in-the-Loop (HITL) and responsible AI approaches provide important foundations, but many remain fragmented across system design, governance, and operational deployment. This paper presents a Three-Pillar (3P) model and framework for developing safe and trustworthy AI agents through transp
arXiv ·
arXiv:2610.30450v1 Announce Type: new Abstract: Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareasoning problem: the model must weigh what further reasoning could achieve against its cost, given what it can already answer. Direct utility training learns a stopping representation at a chosen token price; supporting new prices can require additional controller training. W
arXiv ·
arXiv:2610.30485v1 Announce Type: new Abstract: Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction burden. Reducing this burden requires agents to remember how users want to be assisted. However, existing memory benchmarks focus on factual recall and personalized answers and rarely test how agents learn and act on interaction preferences. We introduc
arXiv ·
arXiv:2610.30488v1 Announce Type: new Abstract: World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolve even when the agent takes no action, and are only partially observed through event logs. We formalize these systems as event worlds and ask whether large language models can predict future observations from the log and the agent's proposed actions. We build complementary benchm
arXiv ·
arXiv:2610.30491v1 Announce Type: new Abstract: LLM agents are often evaluated by reducing execution traces to labels such as final-answer correctness, tool verification, and fault propagation. These labels are measurements produced by parsers, behavioral detectors, and harness rules, and they may not fully capture what the trace shows. We study this in a tool-use setting built on GSM8K, where agents call a calculator whose outputs are occasionally corrupted, giving clear ground truth for what t
arXiv ·
arXiv:2610.30495v1 Announce Type: new Abstract: AI agents now run experiments and report findings, so research produces claims faster than researchers can check them. Each empirical claim implies a property that must hold over its cases, but it states that property only in prose. Without an explicit property, no test can decide which evidence would falsify a claim, so validation cannot keep pace with the claims agents produce. To make claims testable, we approximate a claim's semantics by abstra
arXiv ·
arXiv:2610.30499v1 Announce Type: new Abstract: A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act alone. A harness is a symbolic program that orchestrates calls to the model, handling perception, memory, tool use, recovery, and inference allocation on the model's behalf. ARC-AGI-3 is an interactive benchmark in which agents must explore unfamiliar environments, figure out th
arXiv ·
arXiv:2610.30537v1 Announce Type: new Abstract: Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing benchmark tests whether they can perform the real-world, economically valuable work of a professional physical engineer, such as modelling physics and legal code requirements across a multi-format project corpus, optimising material and installation costs, and issuing 2D/3D
arXiv ·
arXiv:2610.30557v1 Announce Type: new Abstract: LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We study this problem in autonomous investing, where every action is irreversible and based on untrusted Web content. We present Steward, a multi-agent LLM system that draws the boundary of self-evolution in its type system. First, nine role-specialised agents decide jointly: four a