MoreAgentsIsAllYouNeed/AgentForest
We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way of sampling and voting. Our method is called Agent Forest, as a tribute to the classic Random Forest.
Python
Stargazers
- joelgmillerLondon, UK
- CyranoB
- Flyingtiger99
- lijunyou
- Swiftyos
- qw85639229
- Poet-LiBai
- TimePPT
- liu-songBeiJing
- 429196200
- zhimin-zCanada
- SamaelChen
- garyfengUnited States
- digimonsterShanghai
- mikeluckshenzhen
- youyoumingshxsh
- augsevShanghai
- znzjugod
- akan
- 612twilightChina,Nanjing
- LittleRon
- LinXiyao
- Lwt-diamond
- jydm
- rorovicbeijing
- tpnny
- zhangzaibin
- ishan-marikarColombo
- sorokinvldRussia
- infogulchKansas City, MO
- bebetterest
- soasme
- pavelklymenkoSan Francisco Bay Area
- atveitTrondheim, Norway
- lijun20
- tokarev-i-v