Volc Engine Unveils First Agent Package Combining Multimodal Models and Network Tools
On May 11, ByteDance’s Volcanic Engine launched the industry’s first “Agent Package” — the Agent Plan, signaling a shift from single-task programming aids toward general-purpose AI agents. The plan moves beyond traditional single-dimension model subscriptions by weaving together ByteDance’s full‑modal SOTA models (Doubao‑Seed, Doubao‑Seedance, Doubao‑Seedream) alongside third‑party models like GLM‑5.1 and Kimi‑K2.6.

On the technical side, the Agent Plan introduces a “Model + Harness” dual‑drive approach. Beyond multimodal model capabilities, it integrates Harness tools such as online search and Vision Embedding, which boost the agent’s real‑time information retrieval and long‑term memory. To address billing transparency, Volcanic Engine created a unified resource unit called AFP (Agent Fuel Value). The plan now offers four subscription tiers, from Basic to Max; users on Medium and above get free access to the deeply optimized cloud tool ArkClaw.

The Agent Plan lowers the barrier for building complex agent applications through one‑stop resource configuration, and it also shows that large‑model competition is shifting from “base model parameters” toward “toolchain integration and ecosystem deployment.” By tightly coupling Model and Harness, Volcanic Engine aims to create a standardized AI productivity model, accelerating the adoption of agents in diverse scenarios like short‑video production and automated office workflows.
Related article
Ando Launches Team Messaging App Bridging Human and AI Collaboration
In 2025, as Sara Du assisted companies in developing MCP servers, a recurring question emerged: how could teams leverage AI agents directly within Slack? The path was obstructed by significant technical barriers, including the complexity of message s
Sequoia-backed Empirik raises $21M to forecast outages before they strike
Before joining Sequoia Capital in 2020 as chief digital and information officer, Avon Puri spent over a decade running infrastructure at Rubrik and VMware. Three years ago, as large language models began showing their true potential, Puri, alongside
OpenAI launches GPT-5.5 Instant as ChatGPT’s new default model
OpenAI launched GPT-5.5 Instant on Monday, replacing GPT-5.3 Instant as the default ChatGPT model. The company states that this update minimizes hallucinations in high-stakes fields like law, medicine, and finance, while preserving the fast response
Related Special Topic Recommendations
Comments (0)
0/500
On May 11, ByteDance’s Volcanic Engine launched the industry’s first “Agent Package” — the Agent Plan, signaling a shift from single-task programming aids toward general-purpose AI agents. The plan moves beyond traditional single-dimension model subscriptions by weaving together ByteDance’s full‑modal SOTA models (Doubao‑Seed, Doubao‑Seedance, Doubao‑Seedream) alongside third‑party models like GLM‑5.1 and Kimi‑K2.6.

On the technical side, the Agent Plan introduces a “Model + Harness” dual‑drive approach. Beyond multimodal model capabilities, it integrates Harness tools such as online search and Vision Embedding, which boost the agent’s real‑time information retrieval and long‑term memory. To address billing transparency, Volcanic Engine created a unified resource unit called AFP (Agent Fuel Value). The plan now offers four subscription tiers, from Basic to Max; users on Medium and above get free access to the deeply optimized cloud tool ArkClaw.

The Agent Plan lowers the barrier for building complex agent applications through one‑stop resource configuration, and it also shows that large‑model competition is shifting from “base model parameters” toward “toolchain integration and ecosystem deployment.” By tightly coupling Model and Harness, Volcanic Engine aims to create a standardized AI productivity model, accelerating the adoption of agents in diverse scenarios like short‑video production and automated office workflows.
Ando Launches Team Messaging App Bridging Human and AI Collaboration
In 2025, as Sara Du assisted companies in developing MCP servers, a recurring question emerged: how could teams leverage AI agents directly within Slack? The path was obstructed by significant technical barriers, including the complexity of message s
Sequoia-backed Empirik raises $21M to forecast outages before they strike
Before joining Sequoia Capital in 2020 as chief digital and information officer, Avon Puri spent over a decade running infrastructure at Rubrik and VMware. Three years ago, as large language models began showing their true potential, Puri, alongside
OpenAI launches GPT-5.5 Instant as ChatGPT’s new default model
OpenAI launched GPT-5.5 Instant on Monday, replacing GPT-5.3 Instant as the default ChatGPT model. The company states that this update minimizes hallucinations in high-stakes fields like law, medicine, and finance, while preserving the fast response





Home






