Tag
This paper presents TRACE, a query processing framework that models conversational data as temporal evidence graphs to enable state-aware reasoning over evolving user states, improving temporal and multi-hop reasoning for long-conversation QA.
The article argues that AI search quality depends not just on retrieving relevant results, but on correctly routing the query to the appropriate next step, such as follow-up questions, tool invocation, or security checks, making intent classification critical.
A blog post summarizing a panel at the Dutch-Belgian DataBase Day, which discussed practical data systems problems often ignored by academic research, such as variable-length string handling, unrealistic benchmarks, and networking challenges.