← ALB News · curated headline

AppSci-Bench: Can LLMs Build AI Agents and Make Them Better?

arXiv AI · WORLD · AI · 11/20/2026, 12:00:00 AM

arXiv:2611.25360v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used not only to power AI agents but also to build them. While many benchmarks assess the quality of LLM- powered agents, few ascertain how good LLMs are at building them. To this end, we introduce AppSci-Bench, where we construct a setting akin to how human Applied Scientists build agents for businesses - through eliciting task requirements from stakeholders, exploring the business's infrastructure, and scientifically improve the target agent by designing experiments and internal benchmarks. AppSci-Bench features seven realistic domains - five new ones (Slides Generation, Order-to-Cash, Compliance Review, Customer Call Insights, and CRM Insights) and two domains recast from tau3-bench (Yao et al., 2024; Shi et al., 2026b)(Airline and Banking) - each with a held-out evaluation suite customized for that task. We evaluate seven frontier models and find AppSci-Bench challenging: the best model, Claude Opus 5.0, only reaches a mean-minimum score of 59.1% across 3 build attempts; other models do significantly worse. Models struggle with eliciting task requirements (only 65% for Opus 5.0), build representative internal evaluations (models saturate their own evaluation 65% of the time but fail to solve the held-out task), presenting challenges for future research. The benchmark code is available here: https://github.com/sanjari-orb/appsci-bench.

Continue to arXiv AI →

You are being forwarded in 6s — stay on this page