The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams

A new study from researchers including Summer Eunhyung Ann finds that when large language model agents read each other's complete outputs, their proposals converge within one round, erasing the diversity that motivates using multiple models—a phenomenon they call the 'interaction tax.' Testing 11 verifier-scored optimization tasks under matched budgets, the study shows that full-solution interaction is a weak default, while independent proposal generation avoids this collapse, suggesting multi-agent performance depends less on the number of agents than on the information they exchange.

Computer Science Multiagent Systems Submitted on 24 Aug 2026 Title:The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams View PDF /pdf/2608.23541 HTML experimental https://arxiv.org/html/2608.23541v1 Abstract:Does multi-agent LLM interaction help or hurt? Some work reports gains from debate Du et al., 2024 , critique loops Chen et al., 2025 , and mixture-of-agents synthesis Wang et al., 2025 , while other work finds that interaction adds cost without improving quality under equal budgets Tran & Kiela, 2026; Xu et al., 2026; Jarrett et al., 2025 , or that independent sampling already captures multi-agent gains Li et al., 2024 . We argue this contradiction partly reflects a missing distinction, because not all multi-agent communication is equal. Different model families find structurally different solutions, but when agents read each other's complete outputs, their proposals converge within one round, erasing the diversity that motivates using multiple models. We call this the interaction tax. We test 11 verifier-scored optimization tasks under matched budgets and find that full-solution interaction is a weak default. Independent proposal generation avoids this collapse. Full-solution interaction mainly makes agents stay close to the first solution they see instead of trying different approaches, and critique helps only if the violated rule is easy for the LLM to find and fix. These results suggest that multi-agent performance depends less on the number of agents than on the information they exchange, and interaction helps only when agents share the right information at the right time. Submission history From: Summer Eunhyung Ann view email /show-email/8651cf38/2608.23541 v1 Mon, 24 Aug 2026 17:45:15 UTC 684 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators 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 https://info.arxiv.org/labs/index.html .