1
Two AI-based science assistants succeed with drug-retargeting tasks
两大AI科学助手登上Nature，在药物重定位任务上展现超越传统方法的推理能力。
Both tools generate hypotheses; one goes on to analyze some of the data.
2
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
提出假设验证方法定位LLM多智能体系统故障原因，提升系统可靠性
arXiv:2605.17467v1 Announce Type: new Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agent…
3
How to Sell UX Research with Two Simple Questions
用两个简单问题让利益相关者主动认同UX研究价值，搞定预算和优先级。
Do you find yourself designing screens with only a vague idea of how the things on the screen relate to the things elsewhere in the system? Do you lea…