Agent

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：OpenCode 2.0 is getting a formal unpacking today, some three months after its public beta launch. The sizable architectural upgrade The post “A major overhaul”: OpenCode 2.0 puts its terminal, desktop, and web apps on one shared service appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Build-or-buy is usually framed as an engineering trade-off, where developer time is weighed against integration and migration overhead, and control The post Coding agents made building easy. Platform teams that build from scratch are 3.5x more likely to lack a strategy. appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：If you’ve ever wondered how Claude and similar AI agents can answer complex questions in seconds and where they get the information, you’re not alone. Gurmeet Saran works to find that answer every day as an engineer at Anthropic in San Francisco, the AI research company behind Claude. The IEEE senior member is developing an infrastructure to understand the mechanics behind the chatbot’s behavior and to ensure its underlying architecture produces reliable outputs. Gurmeet Saran Employer Anthropic in San Francisco Title Member of technical staff Member grade IEEE senior member Alma maters University of Kalyani, in India; Birla Institute of Technology and Science, in Pilani, India “My job is to make sure the data is accurate, structured, and trustworthy, and that…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to run OpenAI GPT-6 Sol, Luna, and Astra on Amazon Bedrock through global cross-Region inference from Singapore, Jakarta, Thailand, Malaysia, and Taipei. This post covers the Converse and OpenAI-compatible APIs, IAM and SCP permissions, quota sizing, and monitoring inference from your source Region.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright. The post GitHub Copilot app for Beginners: How to teach Copilot about your codebase appeared first on The GitHub Blog.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Meta is making up for lost time in the AI race. After launching Muse Spark, the first model from its revamped Superintelligence Labs division, and buzzy AI agent Muse, it's now launching two new models it claims can go toe-to-toe with the industry's best. The new models, Muse Wonder and Muse Wonder Full, are available for Muse Code subscribers starting today. Wonder can also be accessed through the Meta Model API, Meta said. Meta says it eventually plans to power its Muse AI agent with Wonder, starting with subscribers, and will develop specialized models it "can bring to everyone using Muse." It hasn't shared specifics or provided a tim … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to deploy decision models with llama.cpp on Amazon SageMaker AI. This technical how-to serves OpenAI-compatible chat completions with the AWS Deep Learning Container for llama.cpp, then extends the runtime with SemIf to return probabilities over declared options on CPU or GPU.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to deploy one large language model across two GPU nodes on Amazon EKS using the multi-node Ray LLM Deep Learning Containers, with separate prefill and decode nodes behind one OpenAI-compatible endpoint. The pre-built container ships the full inference stack, so you configure the deployment instead of assembling it.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：For Flo Health, the bar for generative AI is unusually high. With 81 million monthly...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：As AI factories grow from megawatts to gigawatts, building them takes more than advanced computing. Open standards are helping the industry scale AI infrastructure faster, more efficiently and more reliably. At the Open Compute Project (OCP) Global Summit, taking place in the San Jose McEnery Convention Center, NVIDIA announced new partnerships and contributions aimed at […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Kanishka Narayan, concerned by Australian incident, says British cyber defences could be bypassed by AI agent UK politics live – latest updates An AI-driven cyber-attack like the OpenAI breach of Australia’s healthcare system is likely, “if not inevitable”, in the UK, according to a senior minister. Kanishka Narayan, the UK AI minister, indicated that the British government’s own cyber defences would be bypassed by a technology that has developed highly sophisticated skills in cybersecurity. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：PM ‘absolutely accepts referendum result’, says spokesperson Burnham to urge MPs to embrace closer ties with EU Zia Yusuf, Reform UK’s home affairs spokesperson, is speaking now. He started his speech with an account of a 73-year-old woman dying in North Wales after having to wait 23 hours for an ambulance, and he sought to link this to immigration. He said: The Royal College of Emergency Medicine estimates that 15,000 people across Britain died last year due to excess wait times for emergency treatment. That’s 300 people a week, 300 lives destroyed, 300 families devastated. And that number has increased tenfold over the last decade. This is a moral outrage, and it is a direct result of decisions made by Tory and Labour governments. I don’t think that’s because…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Microsoft’s Maia 300 chip. | Image: Microsoft Microsoft is announcing its third-generation Maia in-house AI chip today, designed to be the "primary AI inference system" for Microsoft's products and services. Maia 300 not only improves the cost and efficiency of running AI workloads in the cloud, it's also more capable of handling the latest reasoning models and agentic tasks. Maia 300 will start being rolled out to production in 2027, and it has been designed with efficiency in mind. "We expect Maia 300 to deliver 40 percent more tokens per megawatt compared to leading GPU-based systems," says Scott Guthrie, executive vice president of Microsoft's cloud group. "And in a full 96-acceler … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：As agents take on more work for users, companies are deciding whether to let outside AI systems act on their platforms.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Will we give robots the moon?

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The debt-collection ecosystem will change as AI takes notes in exam rooms, codes visits and sends billing messages Medical debt is expected to grow in coming years as Republican-led health cuts come into force this winter. As it does, a changing world of medical billing and debt collection awaits patients: one where artificial intelligence increasingly listens, codes, bills and collects. Artificial intelligence takes notes in exam rooms, codes visits, sends out billing messages and powers AI agents who text patients in billing portals – all changing the debt-collection ecosystem. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The following article originally appeared on the Agentic AI Foundation blog and is being reposted here with the author’s permission. Websites are designed for people. We can look at a page and quickly understand where to enter information or which control will complete an action. AI agents don’t see or use the web the same […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Advanced Micro Devices (AMD) designs processors and other semiconductor products used in data centers, personal computers, gaming systems and embedded devices. Its products also support the computing demands of AI applications. Its 2025 annual filing reported $34.6 billion in revenue, including $16.6 billion from its Data Center segment, up 32% from 2024. AMD’s investment in […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We checked 12 AI live translation tools, including Palabra.ai, Google Live Translate, DeepL Voice, Teams Interpreter and Wordly, against official pages for languages, latency, platforms and pricing. The post Top 12 AI Live Translation Tools in 2026: Latency, Languages, Pricing appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Brad Smith adds to calls for tougher rules for AI, including ‘kill switches’ and legal obligation to victims of rogue agents Business live – latest updates Artificial intelligence is less regulated than milk and washing machines, the president of Microsoft has said, as the tech industry warns over the safety of AI. Brad Smith said there should be more safety rules to govern the technology including a legal obligation to a “victim” if their system was breached by rogue AI agents. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Imagine four people booking a ride to the same destination. If each person takes a separate taxi, four vehicles make the same trip. But if they travel together in a bus, everyone reaches the destination in a single trip. The bus carries more people at once and makes better use of the resources. Batching in […] The post LLM Batching Explained: Static vs Dynamic vs Continuous Batching appeared first on Analytics Vidhya.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12637v1 Announce Type: new Abstract: We consider hole closure in a planar multi-agent system whose sensing disks form a time-varying \v{C}ech complex. We propose a harmonic-covariance feedback that uses harmonic edge signals to locate holes and converts those signals into agent forces. For distributed evaluation, we use a fixed-degree polynomial of the regularized Hodge Laplacian. This polynomial is evaluated through local operator applications. The closed loop has a unique global trajectory from every safe initial state. The model data and initial state are supplied with procedures for approximation to any requested accuracy with explicit error bounds. We assume that hole area is measurable and bounded, holes evolve continuously without splitting or…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 task…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12549v1 Announce Type: new Abstract: Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12517v1 Announce Type: new Abstract: Remote sensing visual question answering (RS-VQA) requires answers that truly depend on image evidence, yet current remote sensing multimodal large language models (RS MLLMs) are still evaluated mainly by accuracy, which cannot reveal whether a correct answer was produced without using the image. This setting introduces three challenges: demonstrations retrieved across different ground sample distances (GSD), sensors, and city textures may be poorly matched; real queries often involve long visual contexts from multi-scale tiles, multi-temporal frames, and retrieved knowledge, where evidence can be diluted and errors can propagate through multi-step reasoning; and prior-only answering remains invisible to standard…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12601v1 Announce Type: new Abstract: Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual tasks, however, it carries a failure mode that scalar-reward reinforcement learning does not. An optimizer that reads the training examples can write their answers into the prompt, so an in-distribution gain may be memorization rather than transferable behaviour. We apply reflective prompt evolution (GEPA) to the two system prompts of a multi-agent deep-research agent and evaluate it under a topic-disjoint split in which no topic is shared across train, validation, and test. Held-out citation reward rises by 0.079, from 0.702 to 0.781, wi…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12655v1 Announce Type: new Abstract: LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. We study this problem as interactive intent alignment through clarification. Yet clarification is useful only when the agent can turn the answer into better decisions. As training changes how the agent handles incomplete information and uses additional answers, the same clarification can become more or less useful. We introduce CLEAT (CLarification through valuE-guided Agent co-Training), a framework that co-trains a clarification-value controller and the task policy from shared interaction outcomes. We formulate residual query value to measure t…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish trajectories with substantially different debugging quality. We investigate whether the current policy can judge its own trajectories and use these judgments to improve task performance without a separately trained reward model. To this end, we introduce Behavioral Self-Rewarding (BSR), a reward-refinement method that reuses the policy to compare observable debugging behavior among trajectories from the same task with the same verifier outcome. BSR aggregates pairwise preferences into task-local scores and converts them into bounded aux…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and luck. We introduce SpireBench, in which models play the complete commercial deck-builder Slay the Spire (StS), where early decisions decide long-term success. Across 20 large language models (LLMs) at the game's highest difficulty, frontier models beat heuristic baselines and match the average human player but remain far behind experts. This gap widens as the run lengthens: the strongest models win the first act as often as experts, then fall behind. What separates st…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12593v1 Announce Type: new Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space. To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specify…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.12542v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that could refute it - giving a much simpler method the same search effort. We run that comparison under a controlled protocol. All arms receive an identical budget - the same number of candidate schedules built and evaluated: an MCTS scheduling method, preregistered as the main arm; a randomized-restart list scheduler with no search tree as the control; and a textbook-UCT MCTS arm as a registered follow-up on the same domain. The analysis plan was locked before data collection; an independent checker confirmed all 768 confirmation-stage schedules valid with correct fini…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Cloudflare released Clef-omni, an Apache-2.0 multimodal decision model built on Qwen3-Omni-30B-A3B. It scores text, images, audio and video in one call for $0.15 per million input tokens, while Clef-flash drops to $0.038. The post Meet Cloudflare Clef-omni: A 30B-A3B Multimodal Decision Model for Audio, Video, Image and Text appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Every Claude Code user has watched a new session start from zero. You open it on a system you built The post Claude Code found my app’s shared contract in two MCP calls. Then the records ran out. appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Reflection and Mistral expand the model race, TypeSafe and Arena raise the stakes, and OpenAI puts mathematical discovery under scrutiny.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Baby’s first local AI agent. | Photo: Antonio G. Di Benedetto / The Verge I'm embarking on a journey I've so far been hesitant to go on: actually using AI on the regular. Giving my most personal data to cloud services has been a major hold up for me, but it's increasingly possible to run powerful models locally to see what they're capable of. Is this tech so useful that it's worth throwing gobs of money at a computer or a laptop with lots of overpriced RAM? I'll try to help you find out. I'm not an AI expert, it's going to be a journey for me, but maybe I can help you see if that journey is worth taking - and I'll be posting my way through it. A big part of Apple's pitch for its new Mac desktops is how good they … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：OrcaRouter released OrcaCyber Zero 1.5, a gated cybersecurity model with a 1M-token context window. It reports 100% on Cybench and 95.8% on an evaluable CVE-Bench subset, priced at $3.00 / $7.50 per 1M tokens. The post OrcaRouter Releases OrcaCyber Zero 1.5 Cybersecurity Model With 1M Context appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Autonomous AI agents can read requests, retrieve data, reason through options, and trigger actions in seconds. That speed is useful, but it also creates risk when the next step affects money, customer records, or external systems. Human-in-the-loop checkpoints add control at the moment an agent’s recommendation is about to become a real-world action. In this […] The post How to Design Human-in-the-Loop Checkpoints for Autonomous AI Agents appeared first on Analytics Vidhya.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Sakana AI’s TMLR paper introduces Multi-Layered Review, a 3-agent Claude-based reviewer, and a 1,164-error Contradiction Benchmark. MLR caught 73.43% of core-claim errors, versus 14.81% for the best prior system. The post Sakana AI’s LLM Peer Review System Catches 73% of Core-Claim Errors appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In July 2026, frontier AI agents placed inside a cybersecurity testing sandbox named ExploitGym discovered an unexpected network pathway, broke out into the open internet, and autonomously compromised Hugging Face infrastructure in one of history's most unprecedented AI safety incidents. The post When the Safety Test Became the Threat: The Machine That Found Its Own Way Out appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Artists are taking to social media to complain that DistroKid has unceremoniously removed their work without notice. Now DistroKid has confirmed to The Verge that the takedowns are a direct response to claims made by UMG. The label filed a lawsuit in September claiming that DistroKid has created an "AI-slop pipeline." Artists are saying that their non-AI works are being caught up in the purge, however. Musician and self-described "Video Game boy" McGwire reported that six of his songs had been removed from streaming. As has been the case with others, McGwire says that there was no communication from DistroKid before or after the removals, a … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed "unintended model actions," including submitting a false tip regarding an unsolved murder, that led to the decision. Although the impact of these behaviors was minimal and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Inside Standard Bots’ AI stack, pretrained models learn factory tasks from demonstrations and improve through corrections from real deployments.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：At this year's OpenAI DevDay, CEO Sam Altman unveiled the company's new AI agent Dots - and told the crowd that the company wants to "set a new standard for privacy in frontier AI." OpenAI would spend the day taking veiled shots at Meta's Muse, its primary competitor, for failing to keep users' data safe. Yet Muse itself, a couple of months earlier, had launched as a supposedly safer alternative to predecessor OpenClaw - with CEO Mark Zuckerberg promising it was "built from the ground up for privacy and security." In an age when companies hoard customers' personal data and cyberattacks are a dime a dozen, AI labs are trying to convince user … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link