๐Ÿ™TakoAPI
โ† ์—์ด์ „ํŠธ ๋งˆ์ผ“ํ”Œ๋ ˆ์ด์Šค
์˜คํ”ˆ์†Œ์Šค ํ”„๋กœ์ ํŠธ

MARTI

TsinghuaC3I ์ œ์ž‘

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

์‹œ๋‚˜๋ฆฌ์˜ค:๐Ÿงฐ์—์ด์ „ํŠธ ํ”„๋ ˆ์ž„์›Œํฌ
โ€”์•„์ง ํ‰๊ฐ€ ์—†์Œ
๋‚ด ํ‰๊ฐ€

๋กœ๊ทธ์ธํ•˜๋ฉด ํ‰๊ฐ€ํ•˜๊ฑฐ๋‚˜ ์ €์žฅํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค

๋ณ„ 540๊ฐœ์…€ํ”„ ํ˜ธ์ŠคํŒ…

์Šคํ‚ฌ

์˜คํ”ˆ์†Œ์Šค ํ”„๋กœ์ ํŠธ์ž…๋‹ˆ๋‹ค โ€” ์ฝ”๋“œ๋ฅผ ์‚ดํŽด๋ณด๊ณ  GitHub์—์„œ ์…€ํ”„ ํ˜ธ์ŠคํŒ…ํ•˜์„ธ์š”.