Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Interactive Reasoning on ScienceWorld 26 tasks, up to 10 var. (241 ep.)

54Score

RPMS

Updated 1mo ago

Evaluation Results

Method	Links
RPMS 2026.03		54

SOTA Paper

RPMS

RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy

Dataset

ScienceWorld

Follow for update

@wizwand_team Discord

Related Benchmarks

Interactive Decision Making on ALFWorld (qualitative context)Interactive Reasoning on ScienceWorld 30 tasks

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs