Background

1. originally, multi-agent team pre-assigns roles
2. LLMs are heterogeneous, but they are treated homogeneously
3. 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.