Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

2024-07-13 · Shengbin Yue, Siyuan Wang, Wei Chen, Xuanjing Huang, Zhongyu Wei

Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge due to issues such as hallucination, difficulty in acquiring long-tailed knowledge, and limited memory expansion. This paper introduces SMART, a novel multi-agent framework that leverages external knowledge to enhance the interpretability and factual consistency of LLM-generated responses. SMART comprises four specialized agents, each performing a specific sub-trajectory action to navigate complex knowledge-intensive tasks. We propose a multi-agent co-training paradigm, Long-Short Trajectory Learning, which ensures synergistic collaboration among agents while maintaining fine-grained execution by each agent. Extensive experiments on five knowledge-intensive tasks demonstrate SMART's superior performance compared to widely adopted knowledge internalization and knowledge enhancement methods. Our framework can extend beyond knowledge-intensive tasks to more complex scenarios. Our code is available at https://github.com/yueshengbin/SMART.

📄 PDF Abstract BibTeX arXiv:2407.09893

Code (1)

yueshengbin/SMART 공식 구현 pytorch

Tasks

HallucinationNavigate

MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM

2025-09-22 · Woongkyu Lee, Junhee Cho, Jungwook Choi arxiv

Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse wh…

Code Generation

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy

2026-04-20 · Wei Yao, Haohan Ma, Hongwen Zhang, Yunlian Sun 외 arxiv

Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in multi-agent coordination, and limited generalization across …

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

2026-05-17 · Taolin Zhang, Dongyang Li, Chen Chen, Qizhou Chen 외 arxiv

Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinatio…

Question Answering

The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration

2025-10-30 · Kotaro Furuya, Yuichi Kitagawa arxiv

While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition. Howeve…

Community Detection

Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent

2025-05-12 · Ziyang Huang, Xiaowei Yuan, Yiming Ju, Jun Zhao 외

Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabi…

RAG Reinforcement Learning (RL)Retrieval Retrieval-augmented Generation