AI RESEARCH
AsgardBench - Evaluating Visually Grounded Interactive Planning Under Minimal Feedback
arXiv CS.AI
•
ArXi:2603.15888v1 Announce Type: new With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or low-level manipulation. In the landscape of embodied AI benchmarks, AsgardBench targets the capability category of interactive planning, which is sophisticated than offline high-level planning as it requires agents to revise plans in response to environmental feedback, yet remains distinct from low-level execution.