arXiv cs.AI
  • Score 78
  • Official

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

arXiv:2611.23375v1 Announce Type: new 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 d

So what

What this event means by reading role—not a longer recap.

  • BuilderToken accounting that separates work from heat could guide cheaper agent loops, since most tokens in successful runs don't move the requested change.
  • ResearcherThe paper maps coding-agent token costs onto thermodynamic quantities like temperature and free energy, offering a testable framework for agent efficiency.

Score dimensions

Higher total means read first. Each bar is one factor we use to rank the system pool. How we score

RelevanceHow tightly this is about AI.
72
ImpactHow much this could change the field or the market.
45
NoveltyHow new this is versus a recap.
85
CredibilityHow much we trust the source.
82
ActionabilityWhether a reader can do something with it.
40