agentverse 논문리뷰

기존의 한계

Current methodologies for assigning role descriptions to autonomous agents predominantly involve manual assignment, necessitating prior knowledge and understanding of the task. Consequently, the scalability remains ambiguous, especially in the face of diverse and intricate problem contexts.

Specifically, AGENTVERSE splits the problem-solving process into four pivotal stages as shown in Figure 1

문제해결 과정을 네개의 주요 단계로 나누는데

as follows

(1) Expert Recruitment

agent 구성을 결정 , adjustment

(2) Collaborative Decision-Making

문제해결 전략을 device하기 위해 joint discussion에 에이젼트를 engage

Horizontal Structure와

Vertical Structure 탐구

(3) Action Execution

고안된 action을 실행하기 위해 환경과 상호작용

(4) Evaluation

결과물과 desired outcomes와 비교

결과물이 unsatisfactory하다면 next iteration에 피드백이 주어짐

 

피드백 R can either be defined by humans (in a human-in-the-loop (Amershi et al., 2014) setting) or an agent for automatic feedback, depending on the implementation.