{"slug": "tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering", "title": "Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering", "summary": "Researchers analyzing token consumption in LLM-based multi-agent software engineering systems found that code review stages consume the majority of tokens at 59.4%, with input tokens accounting for 53.9% of total usage. The study, which examined 30 software development tasks using ChatDev with a GPT-5 reasoning model, indicates that automated refinement and verification drive costs more than initial code generation. These findings provide a methodology for predicting expenses and optimizing workflows in agentic software engineering.", "body_md": "# Computer Science > Software Engineering\n\n[Submitted on 20 Jan 2026]\n\n# Title:Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering\n\n[View PDF](/pdf/2601.14470)\n\n[HTML (experimental)](https://arxiv.org/html/2601.14470v1)\n\nAbstract:LLM-based Multi-Agent (LLM-MA) systems are increasingly applied to automate complex software engineering tasks such as requirements engineering, code generation, and testing. However, their operational efficiency and resource consumption remain poorly understood, hindering practical adoption due to unpredictable costs and environmental impact. To address this, we conduct an analysis of token consumption patterns in an LLM-MA system within the Software Development Life Cycle (SDLC), aiming to understand where tokens are consumed across distinct software engineering activities. We analyze execution traces from 30 software development tasks performed by the ChatDev framework using a GPT-5 reasoning model, mapping its internal phases to distinct development stages (Design, Coding, Code Completion, Code Review, Testing, and Documentation) to create a standardized evaluation framework. We then quantify and compare token distribution (input, output, reasoning) across these stages.\n\nOur preliminary findings show that the iterative Code Review stage accounts for the majority of token consumption for an average of 59.4% of tokens. Furthermore, we observe that input tokens consistently constitute the largest share of consumption for an average of 53.9%, providing empirical evidence for potentially significant inefficiencies in agentic collaboration. Our results suggest that the primary cost of agentic software engineering lies not in initial code generation but in automated refinement and verification. Our novel methodology can help practitioners predict expenses and optimize workflows, and it directs future research toward developing more token-efficient agent collaboration protocols.\n\n### Current browse context:\n\ncs.SE\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering", "canonical_source": "https://arxiv.org/abs/2601.14470", "published_at": "2026-06-07 01:37:11+00:00", "updated_at": "2026-06-07 01:46:14.601019+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "artificial-intelligence", "machine-learning", "ai-research"], "entities": ["ChatDev", "GPT-5"], "alternates": {"html": "https://wpnews.pro/news/tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering", "markdown": "https://wpnews.pro/news/tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering.md", "text": "https://wpnews.pro/news/tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering.txt", "jsonld": "https://wpnews.pro/news/tokenomics-quantifying-where-tokens-are-used-in-agentic-software-engineering.jsonld"}}