DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning
We propose DHCG, a novel framework that coordinates three modules (Planner, Worker, and Generator) to progressively construct a dynamic hierarchical collaboration graph from scratch based on the query and evolving execution feedback.
ProofPaper ↗
Key points
- LLM-based multi-agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains.
- To address these limitations, we reframe MAS design as a partially observable Markov decision process, in which both the composition and scale of the MAS are dynamically determined.
- We further introduce action-aware preference optimization to train the Planner to make more effective decisions when constructing hierarchical collaboration graphs.
- We systematically evaluate DHCG across code generation, mathematical reasoning, and domain-specific reasoning benchmarks.
Sources (1)
- [1]DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent ReasoningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 06:33 AM
We propose DHCG, a novel framework that coordinates three modules (Planner, Worker, and Generator) to progressively construct a dynamic hierarchical collaboration graph from scratch based on the query and evolving execution feedback.
LLM-based multi-agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains.
Extractive summary: sentences quoted from the sources.
