Doubao Work provides access to Kimi, GLM, and DeepSeek models for corporate clients
Read more
Pandaily
pandaily.com

Doubao Work provides access to Kimi, GLM, and DeepSeek models for corporate clients

Doubao Work, ByteDance's artificial intelligence agent application, announced on October 29th that it is expanding its functionality by providing access to third-party models for business clients. The first group of integrated models includes Moonshot AI's Kimi K3.1 Pro, Zhipu's GLM-5.3, and DeepSeek-V4.1-Flash. These models are now displayed in the application's model list alongside Doubao's proprietary models from ByteDance.

This update applies to team and enterprise subscription plans and is activated by default. Companies are not required to purchase separate access rights from each model developer or submit individual applications. Resource consumption is deducted from the AI credits that the organization already holds in Doubao Work.

Model Access Management

Administrators gain the ability to control which users can use a specific model. They can grant access to individual members, departments, groups, or the entire company. Furthermore, administrators can enable all models from one provider simultaneously or configure the use of a single specific model.

This move changes the positioning of Doubao Work. Previously, the application primarily served as a demonstration of ByteDance's Doubao models within an agent capable of interacting with files, browsers, and desktop applications. By allowing enterprises to direct tasks to competing Chinese models, the core product becomes the agent itself, rather than the underlying model. This also allows teams to choose a model based on the task type, such as using a coding-oriented model for engineering work and another model for handling long documents.

This development aligns with a broader trend among Chinese desktop agent products. This week, Xiaomi added DeepSeek, GLM, Kimi, and Qwen models to its MiMo Desktop, and several other agent tools have made similar moves. For enterprise-level buyers, a unified billing system and standardized permissions for multiple model developers significantly simplify the procurement process, which previously required comparing solutions from different manufacturers.

Doubao Work is continuously expanding its feature set. In recent weeks, capabilities such as saving recorded computer actions as reusable skills, importing chat history, skills, and memory from other AI tools with a single click, and an infinite creative canvas have been added. The application also supports parallel agents and local graphical interface control on Mac.

ByteDance has not specified what other third-party models will follow this initial batch, describing the current composition as the first group of models joining the platform.

Similar stories

Doubao Work and Tencent WorkBuddy Expand Desktop Agent Functionality for Mobile Device Interaction
Read more
pandaily.com

Doubao Work and Tencent WorkBuddy Expand Desktop Agent Functionality for Mobile Device Interaction

Two widely used desktop AI agents in China, Doubao Work and Tencent WorkBuddy, released updates on October 28th aimed at similar goals: ensuring continuous agent operation on the computer even when the user steps away, and providing users with more convenient ways to monitor the process via their phone.

Doubao Work Learns from Demonstration Examples.

ByteDance announced that the capabilities of Doubao Work, its productivity agent, have been improved through more accurate and faster screen clicking. The main new feature is the recording capability. A user can now demonstrate a task on their computer once, narrating the steps as they perform them. After the recording is complete, Doubao Work converts these actions and voice narration into a personalized skill. When a similar task arises in the future, the user selects this skill and only explains the differences, instead of re-describing all the stages.

Previously, Doubao Work could record browser actions as skills, but now this function extends to controlling the entire computer. The second change concerns Mac users. Thanks to a new setting allowing Doubao to operate while the screen is locked, tasks requiring computer control continue to execute after the Mac is locked. A user who leaves their workstation can send a new task to this locked Mac from their phone and view the results there, then resume work after unlocking it.

In recent weeks, Doubao Work has also received several additional features, including chat and memory import from other assistants, a canvas, and parallel agents.

WorkBuddy Adds Real-Time Remote Control Feature.

Tencent introduced a remote control mode for WorkBuddy within the Tencent EdgeOne team's technical support. Launching the mobile application allows connection to the user's computer and displays a live view of the desktop, enabling the user to track every action performed by the agent. This live view is displayed in a small floating window above the chat, while the input field remains active, allowing the user to correct the agent if it deviates from the course.

In full-screen landscape mode, tapping on the phone simulates a click at the same point on the computer and also provides a keyboard panel, common shortcuts, and a virtual mouse for fine adjustments. The setup on Mac requires enabling single-account remote connections and granting screen recording and accessibility permissions. Tencent asserts that only one verified phone can connect to the computer simultaneously, the session runs over an encrypted channel, and user input and remote screen images are not saved, while remote control uses data traffic but not tokens.

Collectively, these updates demonstrate a trend toward developing desktop agents capable of functioning in the background, with the phone serving as a monitoring tool for them.

Alibaba's Qoder Platform Adds Support for LoongArch from Loongson Alongside UOS and Kylin
Read more
pandaily.com

Alibaba's Qoder Platform Adds Support for LoongArch from Loongson Alongside UOS and Kylin

Alibaba's coding platform Qoder now releases builds for Linux ARM64, as well as for the Loongson LoongArch64 instruction set. Furthermore, it has been adapted for the UnionTech UOS Desktop V20 and Galaxy Kylin Desktop V10 desktop systems. The company announced that both the international and Chinese versions received this update on October 23rd, enabling the end-to-end agent workflow from demand to delivery on desktop computers, which is already used by many government and corporate users in China.

The addition of LoongArch support is a significant point in this announcement. Modern Loongson chips utilize a fully self-developed instruction set that is neither ARM64 nor x86, and is not licensed by either party. Releasing the core coding agent for this ISA represents a tangible step in the software stack: developers can invoke tools, edit files, and perform multi-agent tasks on LoongArch machines without needing to switch to a workstation with a foreign architecture.

Support for Linux ARM64 covers a wider range of Arm-based PCs and boards within the same release series. Qoder was first launched globally in August 2025 as an agent-enabled coding platform, including a desktop IDE, CLI, and JetBrains plugins. In May 2026, Alibaba Cloud transformed it from an AI-IDE into a standalone development workstation called Qoder 1.0, and the former assistant Tongyi Lingma was integrated into the productive line for China as Qoder CN. The product family now also includes a mobile client, the QoderWake digital employee tools, and Qoder Cloud Agents.

Alibaba claims that as of August 2026, the product had over 6 million users and more than 100,000 enterprise clients; these adoption figures are company data. With this release, Qoder's presence on desktops in China now covers HarmonyOS PC and HarmonyOS mobile clients, as well as UOS V20 and Kylin V10. For teams using these systems, the practical change is that agent assistance in coding no longer requires a separate x86 environment or cloud environment.

Download information is available on the Qoder website, which provides installation instructions for Linux specifying the new architectures. The essence of this event is not so much the appearance of a new model, but where the agent coding stack is ready to operate. Placing LoongArch alongside ARM64 in one announcement clearly emphasizes the distinction: one line relates to Arm, the other to Loongson's proprietary ISA, and both now receive a first-party Qoder build.

Shanghai AI Laboratory releases full version of Atria Dawn with 512K token context window
Read more
pandaily.com

Shanghai AI Laboratory releases full version of Atria Dawn with 512K token context window

The Shanghai Artificial Intelligence Laboratory has unveiled the full version of its agent-oriented large model, Atria Dawn. This release occurred approximately one month after the preliminary version of Atria Dawn was introduced in mid-September.

The model was trained on the GLM-5.2 base model, which contains 744 billion parameters in a mixture-of-experts format. It is designed to support scientific research and engineering work that requires environmental understanding, tool usage, and multi-step task execution.

The main change noted by the laboratory is the increase in the context window from 256 thousand tokens available in the preview to 512 thousand tokens in the full version. However, the model download table in the project repository on GitHub still lists 256K for both the full model and its FP8 version, so developers are advised to consult the hosted API documentation for the applicable limit.

The laboratory now classifies the model's capabilities into four areas. Discovery involves data collection and systematization, conducting in-depth research, and transforming research questions into executable experiment plans. Creation covers software development, interactive applications, games, machine learning systems, and data visualizations. Delivery allows technical specifications, data, and design requirements to be converted into structured reports and presentations. Cybersecurity focuses on analyzing security issues, vulnerability checking, patch application, and retesting, limited to authorized environments.

Compared to the preview, the laboratory highlights significant improvements: a gain of 7.2 points in JobBench (57.5 vs 50.3), an increase of 2.7 points in WideSearch (84.6 vs 81.9), and an increase of 2.6 points in PaperBench (89.6 vs 87.0). However, the evaluation table in the repository, which the laboratory claims corresponds to its website, shows smaller improvements across most other benchmarks, including AutomationBench (54.7), SkillsBench (67.8), and SWE-bench Pro (61.7). In some tests, the preview showed equal or higher results, such as in BrowseComp, where the preview's 92.5 surpasses the full version's 91.3.

The model is available via hosted APIs with separate international and Chinese endpoints. The repository includes setup guides for SGLang, vLLM, and Codex. The model accepts only text input. The code is released under the MIT license, but the weights for the full version on Hugging Face and ModelScope are currently marked as 'Coming Soon'; only the preview weights are available for download at this time.

Popular