Agents
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New pape…
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually spend money on coding tasks. They ran 8 frontier LLMs on SWE-bench Verified and tracked every token. The findings: - Agentic coding burns ~1000x more tokens than chat or code reasoning, mostly on the input side. - Identical tasks vary up to 30x in token usage across runs. - Higher token spend doesn't buy accuracy. Performance peaks at intermediate cost and saturates. - Models are bad at predicting their own token usage. Self-forecast correlation tops out at 0.39. - Some models burn 1.5M more tokens than others on the same task with no quality gain. If you're shipping agents, runtime cost is high-variance, weakly tied to quality, and unpredictable even by the model itself. That changes how teams budget, route between models, and decide when to kill a run. Paper: https://arxiv.org/abs/2604.22750 Learn to build effective AI agents in our academy: https://academy.dair.ai/
Related
- Ramp is setting the gold standard for AI usage for any company that’s not OpenAI/Anthropic If you’re not tokenmaxxing you’re falling behind
- Pay attention to this one, AI devs, especially if you're thinking about agentic commerce or any agent network where many agents share hosts.…
- Pay attention to this one, AI devs. If you're building multi-agent systems, you're probably wiring static org charts. New research argues th…
- Worth a read if you are building production-grade AI agents.
Source: DAIR.AI (X) | 2026-04-27