Search “Agents”

Matt Palmer demonstrated opening Chrome and real Slack on the Linux remote desktop of a Cursor Cloud Agent, having the Agent generate a Slack UI motion video with code, and then iterating and revising after checking easing and motion patterns against the real interface. He broke the process down into an inner loop (the Agent does the work, checks against the real thing, and fixes) and an outer loop (a human provides references, preferences, and permissions and accepts the output), and proposed t

Matched fieldsTitle

Snaptrude has launched Snaptrude Agent, which can turn design briefs into construction-grade 3D models, covering structure, MEP (plumbing, electrical, and HVAC) and drawings. The agent first presents a plan, then models and draws; everything it adds remains editable, and architects can take over at any time. According to its founder, during the early access phase more than 2,000 designers have run over 25,000 tasks through the agent, and the team has also released AECBench, a benchmark for AEC,

Matched fieldsTitle

Arena's statistics on Agent Arena show that OpenAI's GPT-6.1 Sol (Max) costs $1.91 per task, 85% less than Claude Opus 5.5 (Max) at $12.51 and 87% less than GPT-6 Astra (Max) at $14.93. Arena notes that the sources of these two cost advantages differ: relative to Astra, Sol's advantage comes mainly from a lower token unit price; relative to Opus, it comes mainly from consuming fewer tokens per task. Cost per task is calculated by multiplying the number of input, output, and cache-read tokens by

Matched fieldsTitle

The Hermes Agent open-sourced by Nous Research externalizes learning into files, using MEMORY.md and USER.md to store memory, SKILL.md to store reusable skills, and a wiki to store domain knowledge, while the underlying model weights remain unchanged. The article breaks down its closed-loop learning mechanism, including post-task background review that automatically creates and improves skills. The built-in llm-wiki skill 2.1.0 maintains the knowledge base with a three-layer structure of raw/, w

Matched fieldsTitle

th) Semiconductor Investment Annual Conference and IC Fengyun Awards Ceremony will be held in Chengdu on December 19, 2026, under the theme "Chips Carrying Computing Power · A New Agent Era — The Path of Chip Upgrades in the Intelligent Agent Era." This year's IC Fengyun Awards feature more than 70 awards, covering tracks such as investment institutions, listed companies, AI, embodied intelligence, and automotive electronics. The conference is hosted by the Semiconductor Investment Alliance and

Matched fieldsTitle

On October 29, Akamai released beta versions of two products, Akamai Inference and Akamai Agent Sandbox, allowing users to run AI models on Akamai Cloud and securely execute code generated by AI agents. Akamai Inference supports 12 open-weight models, including OpenAI's gpt-oss-120b, Google's Gemma 4, and Nvidia's Nemotron 3 Ultra, and provides an OpenAI-compatible API. Agent Sandbox is based on WebAssembly isolation technology and restricts code access to computing resources, network connection

Matched fieldsTitle

Microsoft has opened the GitHub Copilot agent harness public preview through the Foundry Agent Service in Microsoft Foundry, offering built-in sandboxes, reusable skills, MCP integration, and sub-agent support; the same harness already supports Copilot Code, Copilot Studio, GitHub Copilot, CLI, and VS Code. When creating a prompt agent, this harness must be selected and cannot be changed afterward; CPU, memory, and idle duration are controlled by Microsoft, and bring-your-own-model is not suppor

Matched fieldsTitle

Matched fieldsTitle

Matched fieldsTitle

Arena.ai says Gemini 4 Carbon ranks 2nd in the real-task-based Agent Arena with a net improvement of 16.2%, and sits on the Pareto frontier for cost, time, and output tokens per task. Compared with Gemini 4 Argon, which ranks 7th with an 11% improvement, Carbon is 5 places higher and 5.2 percentage points better; the gains mainly come from a +13.2 percentage point increase in the positive-feedback-to-complaint ratio, +5.6 percentage points in confirmed success, and +4.8 percentage points in stee

Matched fieldsTitle

Arena's empirical results, based on nearly 9,000 agent sessions, show that OpenAI's GPT-6.1 Terra (Max) ranks 8th in Agent Arena, with a net improvement of +10.6% and a median cost of $0.62 per task. This cost is 43% lower than the $1.09 of 7th-place Gemini 4 Argon (High), 30% lower than the $0.89 of 6th-place GPT-6.1 Sol (Max), and 88% lower than the $5.16 of 5th-place GPT-6 Astra (Max). In the subcategories, it ranks 3rd in Bash Reliability (+13.2%), 7th in Steerability (+13.3%), and 9th in Pr

Matched fieldsTitle

Google has released its flagship model Gemini 4 Carbon, built specifically for continuously running agentic workflows, with a focus on improving coding, agentic, scientific task, and full-stack web development capabilities. The model ranks first on the Artificial Analysis Intelligence Index v5.0 with a score of 59, surpassing Claude Opus 5.5, GPT-6 Astra, and GPT-6.1 Sol; the launch promotional price is $2 per million input tokens and $10 per million output tokens, with a 95% discount available

Matched fieldsTitle

e capabilities of its WorkBuddy enterprise-grade service, including open platform capabilities, enterprise-grade security solutions, an observability center, and WorkBuddy Managed Agent (WMA), with the underlying Agent Runtime upgraded as well. After the upgrade, WorkBuddy can connect to WeCom, Tencent Docs, and systems such as ERP and CRM through MCP and connectors; in addition to Hunyuan, it also supports third-party open-source models and enterprise self-deployed models. Wang Huixing revealed

Matched fieldsTitle

ConnectWise has released RMM Agent, which can inspect associated devices within service tickets, test likely causes, and stage remediation plans from a vetted catalog, with all device changes requiring explicit technician approval. The simultaneously launched Voice, Teams, and Email Agents are used to gather customer information before technical work begins, and all four products are now generally available. Partner RealBytes reports that across more than 500 live tickets, 91% received useful di

Matched fieldsTitle

Siemens has launched an intelligent engineering workflow in which the Fuse EDA AI Agent serves as an MCP aggregation layer connecting to Claude Code, autonomously orchestrating 3D-IC electrothermal co-design, linking seven Siemens EDA tools across nine stages, requiring 100–200 iterations and a total duration exceeding 12 hours. Every decision in this workflow is verified by a deterministic, physics-based EDA solver engine; a single round can cover more than 200 to 500 design points, tool config

Matched fieldsTitle

English text is being prepared.

Matched fieldsTitle

Replit has launched Agent Habitat, allowing agents to access enterprise knowledge and systems within boundaries the company can control, building security governance around four principles: least privilege, fault isolation, auditable production changes, and traceable delegated work. Its credential broker retrieves credentials from the vault and injects them only after each request is authorized, so credentials never enter the agent's context; enterprise connector management supports SAML SSO, SC

Matched fieldsTitle

On October 29, Jinri Yixiu officially released its self-developed physiological signal large model and the ISHO Personal Agent. The latter features 255 data observation items and supports opening MCP to mainstream AI tools. Its energy index model evaluates users' physiological state from three dimensions: sleep performance, nighttime recovery, and previous day's exercise load. Wang Teng stated that the company plans to collect more than 1,000 cases of gold-standard clinical PSG data within one y

Matched fieldsTitle

Cartesia has launched the Managed Agents end-to-end voice agent platform, targeting enterprise call scenarios. On Artificial Analysis's Speech Agent Arena, it ranks first among 30 agents with a preference Elo of 1115. On ServiceNow's EVA-Bench, the platform achieved an accuracy of 87.4% and an experience score of 90.7%, both the highest. The platform co-designs the voice model with the harness, offering capabilities such as 44 languages, tool calling, knowledge bases, and outbound calling batche

Matched fieldsTitle

Akamai has released two services, Akamai Inference and Akamai Agent Sandbox: the former provides 12 open-weight models via an OpenAI-compatible API, with parameter counts ranging from 8B to 2.8T, including NVIDIA Nemotron 3 Ultra, OpenAI gpt-oss-120b, and Google Gemma 4; the latter runs code generated by AI agents in isolation based on WebAssembly, and is released as an open-source component of the Spin framework. Akamai has also expanded its NVIDIA Blackwell Ultra GPU clusters, with each eight-

Matched fieldsTitle