Poster
GPTSwarm: Language Agents as Optimizable Graphs
Mingchen Zhuge · Wenyi Wang · Louis Kirsch · Francesco Faccio · Dmitrii Khizbullin · Jürgen Schmidhuber
Hall C 4-9 #2617
Thu 25 Jul 7:30 a.m. PDT — 8:30 a.m. PDT
Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. Our code is public.