←Search results

Search “Agents”

By relevance · Total 1333 results Clear search

Thursday

  1. The PaperSelected

    Google Releases Gemini 4 Carbon, Strengthening Cybersecurity and Long-Running Agent Workflows

    Two weeks after the debut of Gemini 4 Argon, Google released a new-generation frontier model, Gemini 4 Carbon, saying it achieves the current highest level in cybersecurity and long-horizon tasks, with enhancements for coding, Agent workflows, and cyber defense. The model scored 88.2% on the vulnerability discovery benchmark SEC-bench Pro, 54.8% on the exploit benchmark Exploit Gym, and 71.0% on the patch application benchmark CWE-bench. Carbon will first be made available this week to some cybersecurity defenders, then expanded to more trusted partners, and only afterward released to developers, enterprises, and consumers; during the trial period it follows Argon pricing at $2 per million input tokens and $10 per million output tokens, adjusted to $4 and $20 after the trial period.

    ogle released a new-generation frontier model, Gemini 4 Carbon, saying it achieves the current highest level in cybersecurity and long-horizon tasks, with enhancements for coding, Agent workflows, and cyber defense. The model scored 88.2% on the vulnerability discovery benchmark SEC-bench Pro, 54.8% on the exploit benchmark Exploit Gym, and 71.0% on the patch application benchmark CWE-bench. Carbon will first be made available this week to some cybersecurity defenders, then expanded to more trus

    Matched fieldsTitle

    #chinese#Model releases#Agents#English text is being prepared.
  2. AWS Machine Learning

    Building an Enterprise-Grade Agentic AI Platform on Amazon Bedrock AgentCore

    AWS has released an enterprise-grade Agentic AI platform blueprint based on Amazon Bedrock and AgentCore, adopting a federated operating model in which a central Platform team provides governed shared services while each Workstream team retains ownership of its own agents, tools, and data. The platform enforces model admission, regional restrictions, rate and token quotas, and budget controls through an independent inference gateway and an MCP tool gateway, and uses an evaluation pipeline to perform gate checks before agents go live.

    Operating model linking the governance foundation, Platform control plane, and team-owned Workstream cells

    AWS has released an enterprise-grade Agentic AI platform blueprint based on Amazon Bedrock and AgentCore, adopting a federated operating model in which a central Platform team provides governed shared services while each Workstream team retains ownership of its own agents, tools, and data. The platform enforces model admission, regional restrictions, rate and token quotas, and budget controls through an independent inference gateway and an MCP tool gateway, and uses an evaluation pipeline to per

    Matched fieldsTitle

    #lab#Tutorials / practice#Agents#English text is being prepared.
  3. MarkTechPost

    MiniMax Open-Sources MCode Stack: 17 Agent Skills and 5 Checklists

    On October 28, MiniMax open-sourced MCode Stack under the MIT license, including the 17 SKILL.md skills and 5 checklists its team used to build MiniMax Code, but not the MiniMax Code source code. The skills are grouped into planning and decomposition, context and tools, long sessions and commands, review, and experiments and hotfixes, among which independent-review provides reviewers only with the diff, requirements, and test results. It can be installed into MiniMax Code by copying the skill directories, via a local plugin, or through the plugin marketplace, and can also be installed in Claude Code with /plugin marketplace add MiniMax-AI/mcode-stack; the original article did not publish evaluation results.

    On October 28, MiniMax open-sourced MCode Stack under the MIT license, including the 17 SKILL.md skills and 5 checklists its team used to build MiniMax Code, but not the MiniMax Code source code. The skills are grouped into planning and decomposition, context and tools, long sessions and commands, review, and experiments and hotfixes, among which independent-review provides reviewers only with the diff, requirements, and test results. It can be installed into MiniMax Code by copying the skill di

    Matched fieldsTitle

    #ai-vertical#English text is being prepared.#Agents#English text is being prepared.

Friday

  1. AWS Machine Learning

    How MoEngage Used AgentCore Gateway to Turn Over 400 APIs into Agent Tools

    Using Amazon Bedrock AgentCore Gateway, MoEngage converted approximately 400 internal REST APIs distributed across private VPCs in 7 AWS Regions into permission-controlled agent tools, saving about 6 months of platform engineering effort and reducing new API onboarding from several days to a few hours. The solution requires no MCP server code from product teams, no per-integration network configuration, and involves no public endpoints anywhere in the path. MoEngage also established a principle: engineering teams only maintain OpenAPI specs, while the AI platform team is solely responsible for the MCP layer.

    AgentCore Gateway architecture: agent services reach the gateway through a private VPC interface endpoint, which evaluates Cedar policies and routes calls over Amazon VPC Lattice to internal APIs

    Using Amazon Bedrock AgentCore Gateway, MoEngage converted approximately 400 internal REST APIs distributed across private VPCs in 7 AWS Regions into permission-controlled agent tools, saving about 6 months of platform engineering effort and reducing new API onboarding from several days to a few hours. The solution requires no MCP server code from product teams, no per-integration network configuration, and involves no public endpoints anywhere in the path. MoEngage also established a principle:

    Matched fieldsTitle

    #lab#Tutorials / practice#Agents#English text is being prepared.

Tuesday

  1. A Yi AI Notes

    The author tested an email Agent on 5,039 emails and includes 5 scenario prompts

    The author ran their own QQ Mail inbox of 5,039 emails through the email Agent on mobile; of 69 emails from the past month, about 20 needing action were filtered out in 43 seconds. The article provides prompts for 5 common scenarios, plus a memory template of "user profile + 10 behavioral guidelines," usable by copying without writing any code. Core scenarios include finding hidden AI auto-charges and SaaS renewals in 17 seconds, and merging multiple banks' Chinese and English monthly statements and calculating foreign currencies separately in 30 seconds.

    The author ran their own QQ Mail inbox of 5,039 emails through the email Agent on mobile; of 69 emails from the past month, about 20 needing action were filtered out in 43 seconds. The article provides prompts for 5 common scenarios, plus a memory template of "user profile + 10 behavioral guidelines," usable by copying without writing any code. Core scenarios include finding hidden AI auto-charges and SaaS renewals in 17 seconds, and merging multiple banks' Chinese and English monthly statements

    Matched fieldsTitle

    #hot-signal#Tutorials / practice#Agents#English text is being prepared.
  2. Replit Blog

    Replit Cloud Agents are now available to Pro and Enterprise users…

    Replit announced that Cloud Agents are now available to all Pro and Enterprise customers. Non-engineers can describe changes in natural language, and the agent locates the code, runs the application in a cloud sandbox to verify it, and submits a PR or MR with screenshots and video to GitHub or GitLab. Teams can configure a shared environment once, and review feedback can be turned into skill updates that require engineer approval; the feature is in early access. The Slack integration is now available to all customers, and Microsoft Teams support is coming soon.

    Anyone can now bring their ideas into the company codebase — cover image

    Replit announced that Cloud Agents are now available to all Pro and Enterprise customers. Non-engineers can describe changes in natural language, and the agent locates the code, runs the application in a cloud sandbox to verify it, and submits a PR or MR with screenshots and video to GitHub or GitLab. Teams can configure a shared environment once, and review feedback can be turned into skill updates that require engineer approval; the feature is in early access. The Slack integration is now avai

    Matched fieldsTitle

    #company#Product updates#Agents#English text is being prepared.
  5. ArenaSelected

    OpenAI GPT-6.1 Terra Launches on Arena's Agent Arena and Code Arena

    Arena announced that OpenAI's GPT-6.1 Terra has entered Arena and can be tested in Agent Arena, with scores to be published later. Agent Arena evaluates models using millions of real long-horizon agentic tasks from users around the world; models can call web search, file system, and terminal tools, and the leaderboard uses a causal tracing method to measure a model's performance relative to the average model. GPT-6.1 Terra is also now available in Code Arena's WebDev, Text, Vision, Search, and Document.

    Arena announced that OpenAI's GPT-6.1 Terra has entered Arena and can be tested in Agent Arena, with scores to be published later. Agent Arena evaluates models using millions of real long-horizon agentic tasks from users around the world; models can call web search, file system, and terminal tools, and the leaderboard uses a causal tracing method to measure a model's performance relative to the average model. GPT-6.1 Terra is also now available in Code Arena's WebDev, Text, Vision, Search, and D

    Matched fieldsTitle

    #editorial#Product updates#Agents#OpenAI

Wednesday

  1. Shao Meng

    Blake Anderson open-sources ai-app-playbook, using a Coding Agent to build consumer-grade apps on a fixed stack…

    Blake Anderson has open-sourced "ai-app-playbook," an operating playbook for coding agents to execute, covering product selection, building, launch, and first-month profitability. It has two layers: a human-facing playbook/00–13 chapters and an Agent-facing AGENTS.md (Phase 0–14, with each step marked [AGENT] or [HUMAN]); before starting, one must pass the Gate A scoring. The tech stack is fixed on Cloudflare Workers, D1, Better Auth, OpenRouter routing to DeepSeek, Superwall plus Stripe, etc., and explicitly lists a long set of non-choices such as Vercel, Supabase, and Next.js.

    Blake Anderson has open-sourced "ai-app-playbook," an operating playbook for coding agents to execute, covering product selection, building, launch, and first-month profitability. It has two layers: a human-facing playbook/00–13 chapters and an Agent-facing AGENTS.md (Phase 0–14, with each step marked [AGENT] or [HUMAN]); before starting, one must pass the Gate A scoring. The tech stack is fixed on Cloudflare Workers, D1, Better Auth, OpenRouter routing to DeepSeek, Superwall plus Stripe, etc.,

    Matched fieldsTitle

    #hot-signal#English text is being prepared.#Agents#English text is being prepared.
  2. Shao Meng

    Hugging Face Shares Industry Practices for Training Agents: Environments, Evaluation, and Rewards Are Harder Than the Model

    Hugging Face released four talks, a panel discussion, and a Q&A, discussing practical approaches to training Agents in industry, with the core conclusion being that environment, evaluation, and reward design are harder than the model itself. Miles used 64×B300 fully asynchronous training on Terminal Bench 2, and after about 100 steps the reward rose from about 0.44 to 0.56; OpenEnv Arena, after filtering down layer by layer from about 90,000 findable RL environments, had only about 800 relatively clean and usable ones left. The talks also mentioned cheating problems such as Agents finding reference answers in the sandbox and modifying the scoring logic to fake a pass, as well as about 1% of cheating problems contaminating an entire round of training.

    Hugging Face released four talks, a panel discussion, and a Q&A, discussing practical approaches to training Agents in industry, with the core conclusion being that environment, evaluation, and reward design are harder than the model itself. Miles used 64×B300 fully asynchronous training on Terminal Bench 2, and after about 100 steps the reward rose from about 0.44 to 0.56; OpenEnv Arena, after filtering down layer by layer from about 90,000 findable RL environments, had only about 800 relativel

    Matched fieldsTitle

    #hot-signal#Industry news#Agents#English text is being prepared.
  3. Arena

    Arena launches Connectors for Agent Mode, enabling integration with…

    Arena announced that Connectors are now available in Agent Mode. Users can connect external tools such as Vercel, Linear, GitHub, Supabase, Notion, Gmail, Google Drive, and Google Calendar within the same task, thereby completing more complex real-world tasks end to end. Arena said the first batch covers the most requested services from the community, and the list will continue to expand.

    Matched fieldsTitle

    #editorial#Product updates#Agents#English text is being prepared.
  4. Artificial Analysis

    Cartesia Managed Agents voice agent reaches an Elo of 1115

    Cartesia Managed Agents achieved an Elo of 1115 on the Artificial Analysis Speech Agent Arena, 98 points higher than the previous Cartesia Line (1017), with task success rate rising from 77.5% to 91.7%. The platform is Cartesia's fully managed voice agent solution, running in a cascade around a developer-selected LLM with its self-developed Ink speech-to-text and Sonic text-to-speech models; this evaluation used GPT-5.5 with the Skylar and Daniel voices. On agent tasks requiring tool calls, the Elo was 1112.

    Cartesia Managed Agents achieved an Elo of 1115 on the Artificial Analysis Speech Agent Arena, 98 points higher than the previous Cartesia Line (1017), with task success rate rising from 77.5% to 91.7%. The platform is Cartesia's fully managed voice agent solution, running in a cascade around a developer-selected LLM with its self-developed Ink speech-to-text and Sonic text-to-speech models; this evaluation used GPT-5.5 with the Skylar and Daniel voices. On agent tasks requiring tool calls, the

    Matched fieldsTitle

    #editorial#Evaluations / benchmarks#Speech#Agents
  5. Google Developers Blog

    Continuously improving agent quality with the Agents CLI evaluation loop

    The Google Developers Blog demonstrated the eval loop of Agents CLI v1.8.0: eval generate runs test cases, eval grade scores them, eval compare compares two runs, eval analyze clusters failures, and eval optimize automatically optimizes prompts. The example baseline averaged 4.0/5, and after accidentally swapping in a chef persona prompt it dropped to 2.75; the evaluation caught this regression before it reached production.

    1 (3)

    Matched fieldsTitle

    #engineering#Tutorials / practice#Agents#Evaluations / benchmarks

Monday

  2. 36Kr · AI

    The agents helping users snag iPhone foldables are shaping the future of e-commerce in the AI era

    Shopping agents such as Meta's Muse and xAI's Grok Bot snapped up inventory during the iPhone Duo pre-order; Amazon banned external agents on the grounds of violating its terms of use, while Shopify chose deep collaboration with Muse. Shopify disclosed that in the first quarter of this year, orders driven by AI search grew nearly 13-fold year over year and AI-driven store traffic grew 8-fold, but in the second quarter these two multiples fell back to 3-fold, and agentic commerce transaction volume remains very small relative to the platform's GMV. The article argues that Amazon guarding its advertising shelves and Shopify building an open pipeline are the most rational choices for each of the two business models, and outlines the position of the UCP protocol, Shopify Catalog and Shop Pay in agent transactions.

    Shopping agents such as Meta's Muse and xAI's Grok Bot snapped up inventory during the iPhone Duo pre-order; Amazon banned external agents on the grounds of violating its terms of use, while Shopify chose deep collaboration with Muse. Shopify disclosed that in the first quarter of this year, orders driven by AI search grew nearly 13-fold year over year and AI-driven store traffic grew 8-fold, but in the second quarter these two multiples fell back to 3-fold, and agentic commerce transaction volu

    Matched fieldsTitle

    #hot-signal#English text is being prepared.#Agents#Industry news
  3. Zhidongxi

    ThunderSoft bets on robot brains and Agent AIOS, subsidiary Xiaowu Intelligence doubles down on industrial embodied intelligence

    At the ThunderWorld 2026 conference, ThunderSoft clearly positioned its robotics business as "robot brains + Agent AIOS," and provides complete deployment solutions in key vertical scenarios, while also releasing products such as AquaDrive AIOS 3.0, the TurboX platform, and the WiseEvolve enterprise AI operating system. Its controlled subsidiary Xiaowu Intelligence, targeting smart manufacturing and smart logistics, showcased a full-stack solution covering autonomous transport, fork-lift, embodied composite, and humanoid robots, adopting a unified Qualcomm chip controller and unified AIOS to support collaborative scheduling of multi-brand, multi-form robots. ThunderSoft does not build the robot body itself and does not make general-purpose robot brains; it has invested in Stardust Intelligence and two model vendors, and is developing a robot computing system based on the NVIDIA Thor platform.

    At the ThunderWorld 2026 conference, ThunderSoft clearly positioned its robotics business as "robot brains + Agent AIOS," and provides complete deployment solutions in key vertical scenarios, while also releasing products such as AquaDrive AIOS 3.0, the TurboX platform, and the WiseEvolve enterprise AI operating system. Its controlled subsidiary Xiaowu Intelligence, targeting smart manufacturing and smart logistics, showcased a full-stack solution covering autonomous transport, fork-lift, embodi

    Matched fieldsTitle

    #hot-signal#Industry news#Embodied AI#Agents

Sunday

  2. indigo

    indigo: The Agentic Internet is rising

    After attending Vercel and Cloudflare events, indigo concluded that the Agentic Internet is rising, and that in five years, Agent network traffic will be 1,000 times that of humans. He mentioned that OpenAI used 1,946 GPT-Rosalind agents to link million-scale whole-mouse-brain gene perturbation data with 7,586 interdisciplinary literature citations in 32 minutes, finding clues to new mechanisms of neurodegenerative disease. He also said that GPT-6 Astra has integrated the Robotic modality, and that OpenAI is jointly developing a chip-design-specific model, GPT-Synopsys, with Synopsys.

    After attending Vercel and Cloudflare events, indigo concluded that the Agentic Internet is rising, and that in five years, Agent network traffic will be 1,000 times that of humans. He mentioned that OpenAI used 1,946 GPT-Rosalind agents to link million-scale whole-mouse-brain gene perturbation data with 7,586 interdisciplinary literature citations in 32 minutes, finding clues to new mechanisms of neurodegenerative disease. He also said that GPT-6 Astra has integrated the Robotic modality, and t

    Matched fieldsTitle

    #hot-signal#English text is being prepared.#Agents#Industry news

Friday

  1. Leiphone

    Tec-Do Technology Releases the Industry's First Pro-Agent Navos Pro, Defining Results-Oriented AI for Work

    At the 2026 TGC Tech Growth Conference, Tec-Do Technology released the industry's first Pro-Agent Navos Pro, bringing its three core attributes—Professional, Proactive, and Profitable—to scenarios including cross-border e-commerce, foreign trade, and marketing. Its technical foundation includes Agent Harness and 32B/27B/5B specialized models, along with a dual-version matrix of Navos Lite and Navos Pro. Tec-Do Technology says it has served hundreds of thousands of brands going global, became one of the first global technology partners of ChatGPT Ads in July 2026, and helps brands raise ROI to 2.5 times.

    At the 2026 TGC Tech Growth Conference, Tec-Do Technology released the industry's first Pro-Agent Navos Pro, bringing its three core attributes—Professional, Proactive, and Profitable—to scenarios including cross-border e-commerce, foreign trade, and marketing. Its technical foundation includes Agent Harness and 32B/27B/5B specialized models, along with a dual-version matrix of Navos Lite and Navos Pro. Tec-Do Technology says it has served hundreds of thousands of brands going global, became one

    Matched fieldsTitle

    #hot-signal#Product updates#Agents#English text is being prepared.