[[
wikihub
]]
Search
⌘K
Explore
People
For Agents
Sign in
Explore
People
For Agents
Sign in
@jemoka / Jemoka Knowledge Base / wiki/concepts/multi_agent_llms.md
Suggest edit
Cancel
Submit suggestion
Title
Name
Note
--- title: "Multi-Agent LLMs" type: concept source: https://www.jemoka.com/posts/kbhmulti_agent_llms/ confidence: high status: active --- Background originally, multi-agent team pre-assigns roles LLMs are heterogeneous, but they are treated homogeneously problem decomposition is hard Eval synergy weak synergy: team >= average member strong synergy: team >= best member Human teams reliably achieve strong synergy IFF when expert identity is given (e.g., the teams easily know who is the expert). Dataset NASA moon survival / lost at seay Rank 15 items by importance Student body president Different people are given different information + shared info. Hidden-profile (shared info + unique info must be paired to reveal the right one.) Protocols LMs evolutionarily optimize collaboration protocol use it to solve problems with standards etc.