易星尘
Employers on the program
- 2026阿里巴巴1 talk
Events1
Conferences1
Talks1
Years active2026
Upcoming appearances
Who’s booked ahead? →Event dates shown; only events starting today or later count. 1 upcoming event.
-
AICon 全球人工智能开发与应用大会 | 北京 – · Beijing, China
- AgentLoop 实践：用观测、评估与实验驱动 Agent 持续优化 speaker Program source ↗
No upcoming appearances are currently recorded.
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference)
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Dec 18, 2026 | AICon 全球人工智能开发与应用大会 | 北京 | AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference) | speaker | AgentLoop 实践：用观测、评估与实验驱动 Agent 持续优化 as 阿里巴巴 Agent 上线后，真实任务会不断暴露工具调用、业务规则和上下文理解上的问题。本次分享结合 AgentLoop 实践，介绍如何将这些问题转化为持续优化的数据来源：从运行数据中还原完整轨迹，沉淀评估题库，再结合业务知识生成评估器，由评估 Agent 调用工具查证，给出分数与依据。在此基础上，分析问题出在…Show lessAgent 上线后，真实任务会不断暴露工具调用、业务规则和上下文理解上的问题。本次分享结合 AgentLoop 实践，介绍如何将这些问题转化为持续优化的数据来源：从运行数据中还原完整轨迹，沉淀评估题库，再结合业务知识生成评估器，由评估 Agent 调用工具查证，给出分数与依据。在此基础上，分析问题出在 Prompt、工具还是知识，形成优化建议，并通过同一题库回测验证改动。分享将重点讨论轨迹组装、超长与多模态数据处理、评分稳定性等工程难点，并介绍如何沉淀和复用经验，让评估结果持续用于下一轮改进。 演讲提纲 数据准备：从运行记录到评估题库 采集模型与工具调用… |
Frequent co-speakers
No one else spoke at two or more of the same events.
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.