teresa retweeted
How do we scale up the context of LLMs?
Agentic search scales to arbitrarily large amounts of info, but can easily miss relevant info.
Idea💡: Optimize organization of info for downstream utility. Leads to 30+% gains even on OOD domains
Paper + code: librarian-agents.github.io
Agentic search scales to arbitrarily large amounts of info, but can easily miss relevant info.
Idea💡: Optimize organization of info for downstream utility. Leads to 30+% gains even on OOD domains
Paper + code: librarian-agents.github.io
LLMs deployed in specialized domains, from enterprise codebases to law firms, dig through a mountain of unstructured context!
Our new paper, Librarian Agents, asks: can an agent adapt by curating its own long-context workspace, anticipating queries before they arrive? 🧵⬇️
19
36
324
24,776
teresa retweeted
LLMs deployed in specialized domains, from enterprise codebases to law firms, dig through a mountain of unstructured context!
Our new paper, Librarian Agents, asks: can an agent adapt by curating its own long-context workspace, anticipating queries before they arrive? 🧵⬇️
Our new paper, Librarian Agents, asks: can an agent adapt by curating its own long-context workspace, anticipating queries before they arrive? 🧵⬇️
7
32
176
44,754