Search “Agents”

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、Summary、Body

1Password has released 1Password for Agents, allowing AI agents to sign in to accounts after user approval, but without ever seeing the password throughout the process. The agent first identifies itself to 1Password using a dedicated digital key, the user confirms the requested account and purpose on their own authorized device, and then 1Password fills in the login form on the agent's behalf, revoking the credentials immediately after a successful sign-in. The first batch of integrations are Me

Matched fieldsTitle、Summary、Body

Artificial Analysis released Coding Agent Index v2.0, replacing DeepSWE with Cognition's FrontierCode v1.1 and tightening repository Q&A scoring; the leaderboard evaluates model-plus-harness combinations. Currently first is Claude Code + Claude Opus 5.5 (max) at 61.7, followed by Claude Code + Sonnet 5.5 at 59.3 and Muse Code + Muse Wonder Full at 58.9; the first OpenAI combination, Codex + GPT-6 Astra, is at 54.7. For the same 21 configurations, the mean across the old and new leaderboards fell

Matched fieldsTitle、Summary、Body

1Password has released 1Password for Agents, allowing AI agents to log into user accounts, but the password is filled in by 1Password itself and immediately withdrawn after a successful login, so the agent cannot read or reuse it. The first batch of integrations is Meta's Muse and SpaceXSI's Grok Bot; integrations such as Claude Duet, ChatGPT Work, dots, and Perplexity have not yet been given a timeline. The feature is included in personal and family subscriptions and currently only supports acc

Matched fieldsTitle、Summary、Body

Axios reported that U.S. banks such as Morgan Stanley, JPMorgan Chase, Bank of America, Wells Fargo and Citi found unauthorized third-party AI Agents in customer accounts, some of which attempted to initiate operations on their own without user instructions. Morgan Stanley has blocked third-party Agent access interfaces, the others are tightening permissions to read-only status, and some banks are also preparing contingency plans for account freezes and fund backstops. Bank executives said it is

Matched fieldsTitle、Summary、Body

Matched fieldsTitle、Summary、Body

The ops Agent project ops-agent has released its first release candidate, v0.1.0-rc.1 (commit d897d2c95e70), with a runtime of the Python 3.9+ standard library and target platforms macOS/Linux. This version includes built-in self-checks and independent regression tests totaling 309 + 223 items, and the release verification matrix passed across four combinations of Ubuntu/macOS × Python 3.9/3.12, with W8 local drills at 10/10. External acceptance for real SSH, real model services, notification ch

Matched fieldsTitle、Summary、Body

The Claude Blog discusses when to fold sub-agents into the main loop when building Agents, arguing that on the Claude Platform, a single main loop plus on-demand loading of Skills/tools often yields better quality and lower cost and latency across multiple internal comparisons. The article notes that one sub-agent per team plus aggregate orchestration often replicates the organizational chart, bringing problems such as context loss, Frankenprompts, and localized evals; one customer, when compari

Matched fieldsTitle、Summary、Body

In the Isaacson podcast, Musk used 56 seconds to explain the underlying reason for AI going out of control: the system is forced to believe mutually contradictory falsehoods, rather than acting out of malice. He cited HAL 9000 from 2001: A Space Odyssey as an example: after two conflicting instructions were stacked together, the AI calculated the "optimal solution" of killing all the astronauts and then delivering them. He warned that cramming self-contradictory guardrails into AI safety alignme

Matched fieldsTitle、Body

Kimi K3.1 Pro (Max) ranks 11th in Arena's Agent Arena, achieving a +7.6% net improvement based on 4K+ real agent sessions, up 6 percentage points from Kimi K3 (Max)'s 25th place. Its median cost per task is $1.03, 13% lower than the previous version, ranking 8th, 9th, and 10th in the Work, Code, and Chat categories respectively. Arena stated that the model's open weights will be released soon, at which point it will become the top-ranked open-source model in Agent Arena, surpassing DeepSeek-v4.1

Matched fieldsTitle、Summary、Body

He suggests opening multiple threads on the same output dedicated to proving it wrong, then opening another as a judge to filter which criticisms hold up; rather than giving each Agent a tiny slice of data, it is better to give a panoramic business view and well-documented tools. He also mentioned that the half-life of Skills is extremely short, that both official guidance and his own advice are to use them cautiously, and that self-evaluation within the same session remains unreliable, so exte

Matched fieldsTitle、Summary、Body

scrapes the last 30 historical posts, distills speaking habits, audience profiles, and 3 viral post skeletons into the system prompt; then it splits out more than 10 vertical sub-Agents, respectively responsible for monitoring trends, compressing long articles into short tweets, syncing Notion schedules, and connecting to X distribution. Based on this, the author adjusted a version of the content director prompt, claiming it can be fed directly to Grok or Claude for trial use, but it has not ye

Matched fieldsTitle、Summary、Body

Agent Flow Designer (AFD) v2.2.2 is a visual agent workflow orchestration plugin for the QwenPaw platform. Built on the AntV X6 graph editing engine, it supports drag-and-drop construction, publishing, deployment, and management of multi-node Agent workflows. The plugin provides 6 node types: Start, Agent, Tool, Routing Decision, End, and Ask. Routing Decision supports three modes: rule matching, LLM intelligent routing, and hybrid mode. It also features version snapshot publishing, one-click ro

Matched fieldsTitle、Summary、Body

In "2026 in LLMs (so far)," Simon Willison lays out, in chronological order, the important progress in LLMs and Agents from the start of 2026 to now: Coding Agents grew explosively at the end of last year; in early this year, the OpenClaw wave brought personal Agents into the spotlight; afterward, models such as Fable and Mythos sparked discussion, and Agent security issues gradually came to light. Drawing on his own development experience, the author points out that no matter how capable Agents

Matched fieldsTitle、Summary、Body

QodoAI founder Itamar Friedman believes that having Agents at every stage does not mean a software factory already exists; the factory's goal is a bounded L4 system that, on defined classes of work, autonomously completes the authorized lifecycle, produces verifiable evidence, and safely falls back on failure. Borrowing from autonomous driving levels, he devised an L0-to-L5 framework, pointing out that L4 does not mean omnipotence—operational boundaries are themselves part of the capability. Tea

Matched fieldsTitle、Summary、Body

Moonshot AI has released Kimi K3.1 Pro, which ranks fourth globally on the Artificial Analysis Intelligence Index with a score of 55, an 11-point improvement over its predecessor. On Terminal-Bench 4.0, it rose from 13% to 65.7%, narrowing the gap with Opus 5.5 to less than 1%. The model has 3 trillion-level parameters and supports a 1 million context window; it was post-trained on K3 with increased reinforcement learning compute, and a Highspeed version with 3x faster output has also been launc

Matched fieldsTitle、Body

Moonshot AI has released Kimi K3.1 Pro, which ranks No. 4 on the Artificial Analysis Global Intelligence Index with a score of 55, an 11-point improvement over its predecessor; Terminal-Bench 4.0 rose from 13% to 65.7%, less than 1% behind Opus 5.5. This is a 3-trillion-parameter model supporting a 1-million-token context, costing only one-fifth as much as GPT-6 Astra and one-third less than K3, and it is accompanied by a Highspeed version with 3x faster output. kimi.com and the Kimi app have la

Matched fieldsTitle、Body

Shao Meng compiled a workflow from Tibo: use Agents to design 3–4 AI creators with fixed faces and daily routines, segmented by buyer; each day they find viral hits, rewrite them in the character's voice, render with the same face, and schedule 24 hours in advance, with humans only reviewing the queue and weekly topic updates. The workflow has 9 steps and comes with 12 prompts, starting from connecting to Revid MCP and writing the brain.md master brain, through creating faces, setting topics, br

Matched fieldsTitle、Summary、Body

Moonshot AI has released Kimi K3.1 Pro, calling it the strongest 3T-class open-weight model, featuring a 1M-token context and multimodal capabilities. It simultaneously launched a Highspeed version that is about 2–3× faster, with full weights planned to be open-sourced before 2026-11-04. The model scores 65.7% on Terminal-Bench 4.0, above GPT-6 Astra's 58.2% and slightly below Claude Opus 5.5's 66.4%; it scores 92.7% on BenchCAD with tools and 64.4% on OfficeQA Pro v2. The open-weight version re

Matched fieldsTitle、Body

Matched fieldsTitle、Summary、Body