# AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback

arXiv: https://arxiv.org/abs/2603.15888 · HTML: https://mlsanity.com/paper/2603.15888/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents](https://mlsanity.com/paper/2402.08178/) (2024)
- [ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments](https://mlsanity.com/paper/2407.18550/) (2024)
- [ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models](https://mlsanity.com/paper/2410.14682/) (2024)
- [Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models](https://mlsanity.com/paper/2409.14277/) (2024)

## Built on by (most cited first, 1 of 1)

- [EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2610.13021/) (2026)

## Abstract (arXiv)

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 more 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. Unlike prior embodied AI benchmarks that conflate reasoning with navigation or provide rich corrective feedback that substitutes for perception, AsgardBench restricts agent input to images, action history, and lightweight success/failure signals, isolating interactive planning in a controlled simulator without low-level control noise. The benchmark contains 108 task instances spanning 12 task types, each systematically varied through object state, placement, and scene configuration. These controlled variations create conditional branches in which a single instruction can require different action sequences depending on what the agent observes, emphasizing conditional branching and plan repair during execution. Our evaluations of leading vision language models show that performance drops sharply without visual input, revealing weaknesses in visual grounding and state tracking that ultimately undermine interactive planning. Our benchmark zeroes in on a narrower question: can a model actually use what it sees to adapt a plan when things do not go as expected?