How Well Does Agent Development Reflect Real-World Work?
This work addresses the problem of misaligned AI agent development for researchers and policymakers by highlighting gaps in benchmarking relative to real-world work.
The study systematically analyzed the alignment between AI agent benchmarks and the U.S. labor market, revealing substantial mismatches where agent development is programming-centric while human labor is concentrated in other areas, and proposed principles for designing better benchmarks.
AI agents are increasingly developed and evaluated on benchmarks relevant to human work, yet it remains unclear how representative these benchmarking efforts are of the labor market as a whole. In this work, we systematically study the relationship between agent development efforts and the distribution of real-world human work by mapping benchmark instances to work domains and skills. We first analyze 43 benchmarks and 72,342 tasks, measuring their alignment with human employment and capital allocation across all 1,016 real-world occupations in the U.S. labor market. We reveal substantial mismatches between agent development that tends to be programming-centric, and the categories in which human labor and economic value are concentrated. Within work areas that agents currently target, we further characterize current agent utility by measuring their autonomy levels, providing practical guidance for agent interaction strategies across work scenarios. Building on these findings, we propose three measurable principles for designing benchmarks that better capture socially important and technically challenging forms of work: coverage, realism, and granular evaluation.