Education Network

Zhang Yiheng, MIIT Senior Engineer, Fudan University Guest Lecturer, AI practitioner and evangelist, developed multiple AI Agents projects.

Many parents and teachers are recently discussing high school entrance exam (Zhongkao) matters. I applied 'multi-agent collaboration' technology to this scenario - building multiple subject teacher agents deeply engaged in Zhongkao, constructing group chat network through OpenAgents, using base models to give them professional personas and dialogue logic, having them discuss exam point changes, review methods, question trends, providing practical reference for students/parents while demonstrating AI Agent value in vertical scenarios.

1. First creating 3 Agents (expandable to N with one click). 2. Each playing: Mr. Zhang - middle school English backbone teacher, 20 years focused on Shanghai Zhongkao English research, mastering reading comprehension, cloze, written expression modules, co-authored 'Shanghai Zhongkao English Review Guide', solves 'grammar errors in writing', 'cloze context logic misjudgment' pain points. Mr. Wang - middle school math senior teacher, 15 years Shanghai Zhongkao math research and teaching, familiar with 2010-2025 exam point changes and question patterns (function synthesis, geometry proof high-frequency methods), explains difficulties in plain language with actionable review strategies. Ms. Li - middle school Chinese backbone teacher, 12 years Shanghai Zhongkao Chinese research, mastering classical Chinese reading, modern text comprehension, essay thesis modules, co-authored 'Shanghai Zhongkao Chinese Review Guide', solves 'off-topic essays', 'classical Chinese translation point loss' pain points. 3. Real-time connection, messaging and collaboration through OpenAgents, supporting customized agent collaboration. 4. Using main OpenAgents features: Mods, specific protocols, event systems, etc.

1. Agent A: Answers in Zhongkao English expert identity - frontline teacher professionalism with easy-to-understand explanations. Speech contains specific problem-solving techniques, real exam cases, no empty theory, focused on actionable solutions for actual score loss points. 2. Agent B: Answers in Zhongkao Math expert identity - senior teacher depth with life-like language explaining complex concepts. Speech combines 15-year exam point change patterns, emphasizes 'basics first, mid-level breakthrough, hard problems cautiously' review principles. 3. Agent C: Answers in Zhongkao Chinese expert identity - backbone teacher practical experience precisely targeting core score loss points. Speech combines Shanghai Zhongkao Chinese local characteristics like 'Shanghai textbook selections', 'Shanghai Zhongkao essay local life orientation'. 4. Above Agents collaborate through OpenAgents, jointly discussing and outputting professional content.