Boundless Agents
Overview
Focus on high-frequency scenarios such as personal devices, automotive and mobility, financial services, education, and industrial manufacturing, and explore runnable, demonstrable, and replicable agent applications.
The Boundless Agents track focuses on real-world deployment of AI Agents in industry scenarios. It encourages teams to build agent applications for high-frequency scenarios such as personal devices, automotive and mobility, financial services, education, and industrial manufacturing, with capabilities including task understanding, workflow orchestration, tool calling, knowledge enhancement, multi-turn interaction, and result delivery. Multimodal entries are especially welcome.
This track does not encourage generic chatbots, single-point Q&A tools, or simple content generators. Instead, entries should target real users, real business workflows, and real closed-loop tasks, validating how AI Agents can enter industry environments, improve efficiency and experience, and form application prototypes with sustained usage value.
Prize Information
*The winner of the Grand Award will be selected from the four track champion teams.
Additional Awards
Topic Directions
Native agents for next-generation personal intelligent terminals
Focus- First-person perspective, voice interaction, real-time perception, always-available companionship, and lightweight feedback
Intelligent vehicle agents for the full owner lifecycle
Focus- Vehicle purchase, usage, maintenance, after-sales service, travel, and in-cabin experience closure
Financial-service agents for business operations and risk analysis
Focus- Document understanding, rule matching, risk alerts, investment research organization, and workflow assistance
Education agents for personalized learning and teaching assistance
Focus- Personalized learning, homework support, learning diagnosis, teacher lesson preparation, and learning companionship
Industrial agents for equipment operations and supply-chain collaboration
Focus- Equipment, quality, work orders, inventory, production scheduling, and supply-chain coordination
Core Work Requirements
Core Work Requirements
- Entries should complete at least one demonstrable and verifiable closed-loop task, and clearly explain target users, scenario pain points, interaction flow, technical approach, data sources, compliance boundaries, and future iteration plans.
- Entries should address one of the five industry topics, or propose a refined scenario based on real needs that aligns with the track positioning. Generic Q&A, content generation, or concept-only demos without user workflows should be avoided. A runnable demo, video demonstration, or equivalent verifiable material is required.
- Entries should explain the models used, agent architecture, tool interfaces, knowledge bases, data processing, and deployment approach, and clearly state data authorization, privacy protection, risk warnings, and industry boundaries. Open, reusable application templates, tool components, sample data, or technical documentation are encouraged.
Submission Requirements
Detailed submission requirements are as follows:
*The schedule may be adjusted flexibly according to actual progress and is subject to the committee’s final notice.
Review Focus
Projects will focus on the following areas:
- Industry scenario value
- Agent capabilities and closed-loop task execution
- Product experience and demo completeness
- Technical implementation depth and engineering reproducibility
- Safety, compliance, and open reuse value
Participant Support
This track will provide development resource support to participating teams that complete their preliminary-round submission and pass the submission validity review. The support may include computing resources, cloud services, or equivalent competition-related resources, with a maximum value of RMB 200 per team. Support will be allocated based on teams' overall preliminary-round scores, with no more than 300 allocations available per track in principle. After the preliminary-round submission deadline, the Organizing Committee will notify eligible teams via email or official competition community channels to submit the required materials, based on the submission and review results, and will distribute the resources accordingly. This resource support does not constitute a competition prize and will not affect evaluation scores or qualification for advancement. The specific forms of support, eligibility criteria, documentation requirements, distribution procedures, and timeline shall be subject to further notice from the Organizing Committee.
Best-fit Teams
- This track is open to global developers, startup teams, university students, research teams, enterprise technical teams, product teams, and open-source community members. It is especially suitable for interdisciplinary teams familiar with scenarios such as glasses, automotive, finance, education, and industrial manufacturing, and capable of completing interaction design, data preparation, tool calling, and result validation around real user needs.