via “research context management with incremental knowledge accumulation”
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. [#opensource](https://github.com/stanford-oval/storm/)
Unique: Explicitly models research context as a first-class artifact that accumulates across turns, enabling the system to detect redundant queries and build on previous results. Rather than treating each research turn independently, the system maintains continuity and uses context to guide future research.
vs others: More efficient than stateless research systems because it avoids re-researching the same topics and uses accumulated context to guide follow-up queries, reducing total API calls and improving research coherence.