aiqbench analysis
This research introduces RGA-Designer, a reinforcement learning approach that optimizes communication topologies in LLM-based multi-agent systems to significantly reduce token consumption without sacrificing task accuracy. By explicitly rewarding structural compactness during training, the method addresses inefficiencies in previous autoregressive graph generation techniques, offering a practical path toward more scalable agent coordination.
Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
arXiv:2608.20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse and efficient topologies. We address this limitation by introducing a Reward-Guided Autoregressive Graph Generation (RGA-Designer) inspired by Reinforcement Learning from Human Feedback (RLHF). We train a reward model that jointly captures task correctness and structural compactness, and then fine-tune the pretrained graph generator using the reward model as feedback. Our method preserves task accuracy at the level of ARG-Designer while reducing token consumption by an average of 20.5%.
Abstract:LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse and efficient topologies. We address this limitation by introducing a Reward-Guided Autoregressive Graph Generation (RGA-Designer) inspired by Reinforcement Learning from Human Feedback (RLHF). We train a reward model that jointly captures task correctness and structural compactness, and then fine-tune the pretrained graph generator using the reward model as feedback. Our method preserves task accuracy at the level of ARG-Designer while reducing token consumption by an average of 20.5%.
Multiagent Systems (cs.MA); Computation and Language (cs.CL); Machine Learning (cs.LG)
arXiv:2608.20099 [cs.MA]
(or arXiv:2608.20099v1 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2608.20099 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 221 words
Related coverage
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier
Latent Space · Sep 1, 2026
Senior SWE-Bench: Evaluating Coding Agents Like Senior Engineers
Snorkel AI Blog · Jul 16, 2026
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems
arXiv · Sep 3, 2026