Back to Hackathon Showcase
#124
Hacker Pioneer AwardPrize: ¥100#124
Thesis Pilot Network
This project builds a 'Thesis Full-Process Assistance Agent Network' based on OpenAgents. Targeting pain points of difficult thesis topic selection, unclear technical routes, and non-standard proposal...
About the Creator
Not participating
Project Description
This project builds a 'Thesis Full-Process Assistance Agent Network' based on OpenAgents. Targeting pain points of difficult thesis topic selection, unclear technical routes, and non-standard proposal writing for college students, it provides one-stop service from topic recommendation, plan design to report generation. Core innovation: 'Core Agent fallback + Specialized Agent collaboration' mechanism. When specialized Agents don't respond, core Agent auto-fills, ensuring user questions always get answered. Using precise event filtering for 'zero-interference' efficient collaboration, greatly improving response stability and UX.
Technical Solution
Agent Planning: 1 Core Agent (ID: thesis_agent). Role: Senior thesis advisor. Responsibilities: Full-process assistance including topic recommendation, technical route planning, proposal writing guidance and Q&A. Collaboration: 'Single-agent closed-loop' mode. This Agent handles all user consultations from 'topic selection' to 'proposal' as comprehensive assistant. Collaboration logic reserved for future specialized Agents (like code assistant), handles comprehensive questions or provides 'fallback' ensuring users always get responses. Key OpenAgents features: Event System using thread.channel_message.notification for user message listening, filter mechanism responding only to human users ignoring other Agent messages; Mods extension using messaging Mod for efficient communication; gRPC protocol for stable, efficient instruction transmission.
Features
① Full-process thesis guidance: Generates compliant topics, technical routes and proposal drafts based on user's major and tech stack. ② Smart information guidance: Proactively guides users to supplement key details (like expected difficulty) when info is incomplete. ③ Precise message filtering: Only responds to human user consultations, auto-ignores other Agent messages, preventing invalid multi-agent interactions. ④ Collaborative fallback response: In multi-Agent environment, only intervenes for comprehensive questions when specialized Agents (like code Agent) don't respond. ⑤ Mod communication integration: Uses messaging Mod for standard message send/receive between agents and users.
Inspired by this project?
Build your own multi-agent system with OpenAgents. Join the community and start creating today.