titleGBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
authorsXiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür, Gokhan Tur
date2026-06-26
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.28187
affiliationUniversity of Illinois at Urbana-Champaign
upvotes13 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractMulti-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tasks through role specialization and structured interaction. However, their performance is often limited by miscoordination and, more fundamentally, the lack of fine-grained credit assignment across agents. Existing approaches typically rely on coarse-grained feedback, making it difficult to identify which agents or interaction steps are responsible for errors. We propose Gradient-Based Connections (GBC), an approach for fine-grained attribution and optimization of multi-agent systems. GBC models a MAS as a computational graph and introduces gradient-based connection weights to quantify the influence of each agent's output on downstream agents at the token level. By constructing an attribution graph and propagating task-specific loss signals backward, our method enables precise identification of error sources and targeted prompt optimization. We further develop AgentChord, an efficient implementation that leverages prefix-based gradient computation. Experiments on MultiWOZ and τ-bench show that GBC improves multi-agent performance and outperforms strong single-agent and multi-agent baselines, and higher attribution quality is associated with greater optimization effectiveness. Code is available at: https://github.com/yxc-cyber/AgentChord.

cite

@misc{yang2026gbc,
  title={GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems},
  author={Xiaocheng Yang and Abdulrahman Alrabah and Dilek Hakkani-Tür and Gokhan Tur},
  year={2026},
  eprint={2606.28187},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.28187}
}