SOURCE-LINKED INTELLIGENCE

Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasks

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Agentic coding workflows are now widely deployed in real-world systems. With long-horizon reasoning and tool use, token usage has become an important consideration for both cost and efficiency. Two engineers using AI will solve the same problem differently. How the specification of a task shapes an agent's token spend, and whether that spend can be predicted in advance, are open questions. Here, we study the effects of different task specifications on agentic token spend with the Kimi K3 model at three thinking efforts. Across $2,700$ runs, we show that reducing a full task specification to a

Read original source ↗ Open in workspace

recordType

paper

region

Global