← Back to the wire

AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

AchievementBenchmarkJul 10, 2026

Jiayu Liu and co-authors submitted AdaPlanBench to arXiv on June 4, 2026. The paper, titled "AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints," presents a benchmark for assessing adaptive planning capabilities in LLM agents. A revised version was posted on July 9, 2026. The work is categorized under cs.CL and was issued a DOI through DataCite.

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01medPRIMARY
AdaPlanBenchModelJiayu LiuPerson
Canonical: https://arxiv.org/abs/2606.05622