# 80% of coding agent tokens are wasted as heat

> Source: <https://www.snipvote.com/story/cmwn879q00002b5bg86ukjrey>
> Published: 2026-11-19 07:43:14.081272+00:00

**Recommendation:** Cut sampling temperature and constrain exploration in coding agents to eliminate unproductive token spend; the paper measured 80% of tokens as wasted and a 4–5x cost reduction without correctness loss.
More in the playbook "Controlling LLM cost": <https://wpnews.pro/playbooks/llm-cost>

[arXiv](https://arxiv.org/abs/2611.23375)

### 80% of coding agent tokens are wasted as heat

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

80% of tokens in agentic coding runs are wasted as "heat"—model calls that don’t change the code but still burn budget. This means your per-task token cost is 5–7x higher than the actual work done, and sampling temperature directly drives that inefficiency. Optimizing for thermodynamic "free energy" (the 14–22% of tokens that actually advance the task) could cut your cloud spend by 4–6x or let you ship agents that handle 5x more complex repos on the same budget.

80% of tokens in agentic coding runs are wasted as "heat" on model calls that don't change the final output, meaning most LLM compute is spent on unproductive exploration. This reveals a direct optimization lever: reducing sampling temperature or constraining exploration could cut token costs by 4–5x without impacting correctness, making agent workflows far cheaper to run in production.
