跳到正文
arXiv cs.AI· Al\'an Aspuru-Guzik, Varinia Bernales·· 36 分钟前AI 评分50

arXiv 论文提出“软件热力学”:解析编码智能体 token 消耗中的热、熵与错误

Where the Tokens Go: Heat, Entropy and Error in Agentic Coding

AI 导读

arXiv 论文提出“软件热力学”理论,借鉴经典与随机热力学分析编码智能体的 token 消耗,将其划分为“功”与“热”。

正文 · 原文

View PDF HTML (experimental)

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.
Comments: 43 pages, 10 figures, 11 tables; includes supplementary information with 3 further figures
Subjects: Artificial Intelligence (cs.AI); Statistical Mechanics (cond-mat.stat-mech); Software Engineering (cs.SE)
ACM classes: D.2.8; I.2.2
Cite as: arXiv:2611.23375 [cs.AI]
  (or arXiv:2611.23375v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23375

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Alán Aspuru-Guzik [view email]
[v1] Tue, 17 Nov 2026 19:00:02 UTC (2,298 KB)

来源:arXiv cs.AI · arxiv.org