#MCP/工具调用

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.

The open-weight labs did not come to play this week. StepFun dropped Step 3.7 Flash. MiniMax dropped M3. Both with open weights, both already live in Kilo. The "model wars" just got a lot more interesting.

Tencent moves closer to launching AI agent for WeChat’s 1.4bn Chinese users https://ft.trib.al/bto5t0c

New video of Qualcomm CEO Cristiano Amon: AI will require “gazillions” of tokens. Because, Agentic AI will consume dramatically more tokens because it performs autonomous tasks, uses multiple systems, and interacts with tools. AI demand will grow hugely when software starts letting agents act, not just answer. A chatbot spends tokens on language; an agent spends tokens on deciding, checking, calling tools, reading outputs, revising plans, and coordinating with other software. Today a single human-AI exchange may be large, a reasoning task may be much larger, but we are already entering the agentic era, where an autonomous workflow can become exponentially larger still because the model is no longer producing one response. It is running a process. When a SaaS product redesigns itself around human-agent interaction, every task can become a chain of hidden micro-decisions, and each micro-decision consumes context, memory, tool calls, verification, and output tokens. Another point is people hear “more tokens” and think only of bigger data centers, when the deeper change is economic: software usage may stop being measured mainly by clicks, seats, or sessions. It will be measured by how much machine reasoning/tokens gets spent on behalf of each user. ---- From "Reuters" YouTube channel, (link in comment)

Today @MiniMax_AI ships M3 — the first frontier model purpose-built for computer-use agents. Natively multimodal. One model, almost every real-world task. And today, @sai_borg runs it. Our users are the first to use M3 the way it was designed to be used — on a real desktop, doing real work. This is what model-and-agent alignment looks like. → Try it: http://sai.work

Goldman Sachs: "Token use by AI agents is expected to multiply 24 times by 2030" AI agents are now creating the first serious cost test for the AI boom. As was reported this week, Uber and Microsoft are already rethinking expensive agent usage. A chatbot may answer once, but an agent plans, calls tools, checks results, edits mistakes, and repeats the loop. That loop can make one user request consume 10x, 50x, or even far more tokens than a normal answer. Goldman’s bullish case is that monthly token use could reach 120 quadrillion by 2030, while inference cost per token keeps falling 60%-70% per year. The fight is now between agent productivity and token waste. Earlier this month, Microsoft began revoking developer access to Claude Code, with plans to move them to its in-house Copilot Command Line Interface tool by June 30. The company has framed this as consolidating teams around its own tools, but the timing at the fiscal year’s end hints it may also be about lowering costs.

Update: We didn't get the blog out yet. It's been a busy weekend. But @StepFun_ai Step 3.7 Flash is currently FREE in Kilo. 👀 Enjoy!

Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20b on tool calling We ran both locally on a MacBook Pro M5 Max, 64GB, and gave each the same trip-planning request that only completes if the model fires all 7 tool calls - weather for 3 cities, two currency conversions, an email and a reminder Outputs: LFM2.5-8B-A1B: 4.8 GB RAM usage, 7/7 tool-calls, 266 tok/s, 6.9s OpenAI gpt-oss-20b: 11 GB RAM usage, 3/7 tool-calls, 146 tok/s, 15.0s The 8B used less than half the RAM and still fired all 7 calls, while the 20B silently dropped more than half of its own. It also ran ~2x faster, wrapping the full agentic request in 6.9s against 15s. That's what 38T training tokens buy: a 1B-active MoE that nails the agentic tool calls a model 2.5x its active size keeps dropping

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! @googleaidevs @GoogleAIStudio

🚀 The team at @Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: https://github.com/run-llama/antigravity-demo Get started with LlamaParse: https://cloud.llamaindex.ai/signup

Excited to support Step 3.7 Flash by @StepFun_ai on ZenMux from day one. 🚀 A sparse MoE vision-language model built for agentic, coding, search, multimodal, and long-context workflows. ⚡ 400 TPS, ~11B active params, 256K context, 3 reasoning levels 👁️ understands UIs, charts, docs, and images — then writes code or calls tools to act on what it sees 🔎 built for deeper web + visual search, with more sources and follow-up 🛠️ reliable tool use: less drift, fewer broken tool calls, 98%+ on τ²-bench across difficulty levels 🧠 works with Claude Code, KiloCode, Hermes Agent, OpenClaw, and MCP-style workflows 🖥️ runs locally on Mac Studio M4 Max, DGX Spark, and AMD AI Max+ 395 Try it on ZenMux now → https://zenmux.ai/stepfun/step-3.7-flash One API for capable models. #StepFun #ZenMux #AIAgents #LLM