80% of Coding-Agent Output Tokens Were Spent on Calls That Didn't Change Code A paper submitted to arXiv on 17 November 2026 by Alán Aspuru-Guzik and co-authors reports that about 80 per cent of the tokens in a successful coding-agent run are generated in model calls that leave the requested code change unchanged, which the authors call "heat." The paper, "Where the Tokens Go: Heat, Entropy and Error in Agentic Coding," estimates a change's free energy at 14 to 22 per cent of the mean cost of a successful run and finds coding costs 1.1 to 1.5 times as much as undoing the same change. The authors propose a "software thermodynamics" framework that splits token cost into work and heat, with the test suite acting as a Maxwell's daemon judging each change, and suggest it could yield new tools for analysing and optimising coding agents. Computer Science Artificial Intelligence Submitted on 17 Nov 2026 Title:Where the Tokens Go: Heat, Entropy and Error in Agentic Coding View PDF https://arxiv.org/pdf/2611.23375 HTML experimental https://arxiv.org/html/2611.23375v1 Abstract:Coding agents are billed by the token, yet software engineering says nothing about what a token actually buys. Here we introduce a theory of software thermodynamics. The theory draws analogues from classical and stochastic thermodynamics, extends them, and applies them to modern agentic coding. We count the tokens an agent generates as its cost and divide that cost into work and heat. The test suite acts as a software Maxwell's daemon that judges every coding change. We test the theory with an analogue of the experiments in which a single molecule is pulled open and let fold again: an agent makes a change to a repository coding and then undoes it uncoding , many times over, and we count the tokens of every model call. The cycle returns the requested edits to where they began, with each direction started from a stored reference tree, and the spread of its cost over repeated cycles defines a software temperature, which rose with the sampling temperature of the model. About 80 per cent of the tokens of a successful run are generated in model calls that leave the requested change where it was, and we call these tokens heat. The free energy of a change, which we estimate by analogy with the equality of Jarzynski, is 14 to 22 per cent of the mean cost of a successful coding run. Coding costs 1.1 to 1.5 times as much as uncoding. The daemon is imperfect: the verdict of a test suite varies with its environment, and a suite that accepts a broken change has a cost in tokens. The practical implication of the proposed theory could be new tools for analysing and optimising coding agents through the lens of thermodynamics. Submission history From: Alán Aspuru-Guzik view email https://arxiv.org/show-email/cce0f9f8/2611.23375 v1 Tue, 17 Nov 2026 19:00:02 UTC 2,298 KB Additional Features Current browse context: cs.AI Change to browse by: 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 .