Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
원문 초록
Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods. We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness in LLM-based MAS through LLM training. Optima employs an iterative generate, rank, select, and train paradigm with a reward function balancing task performance, token efficiency, and communication readability. We explore various RL algorithms, including Supervised Fine-Tuning, Direct Preference Optimization, and their hybrid approaches, providing insights into their effectiveness-efficiency trade-offs. We integrate Monte Carlo Tree Search-inspired techniques for DPO data generation, treating conversation turns as tree nodes to explore diverse interaction paths. Evaluated on common multi-agent tasks, including information-asymmetric question answering and complex reasoning, Optima shows consistent and substantial improvements over single-agent baselines and vanilla MAS based on Llama 3 8B, achieving up to 2.8x performance gain with less than 10\% tokens on tasks requiring heavy information exchange. Moreover, Optima's efficiency gains open new possibilities for leveraging inference-compute more effectively, leading to improved inference-time scaling laws. By addressing fundamental challenges in LLM-based MAS, Optima shows the potential towards scalable, efficient, and effective MAS (https://chenweize1998.github.io/optima-project-page).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models
Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.