← 研踪 PaperTrailarXiv:2611.25360 · v1
AppSci-Bench: Can LLMs Build AI Agents and Make Them Better?
首次提交 2026-11-19 09:58
版本更新 2026-11-19 09:58
雷达观测 2026-11-20 10:50
摘要
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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-19 09:58 · 最新观测版本
AppSci-Bench: Can LLMs Build AI Agents and Make Them Better?
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.
查看此版本解读 →查看此版本原文 ↗