Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908976098050048 |
|---|---|
| author | Huang, Sukai Zhang, Chenyuan Ke, Fucai Cai, Zhixi Haffari, Gholamreza Qu, Lizhen Rezatofighi, Hamid |
| author_facet | Huang, Sukai Zhang, Chenyuan Ke, Fucai Cai, Zhixi Haffari, Gholamreza Qu, Lizhen Rezatofighi, Hamid |
| contents | Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction, making it difficult to study how agent behavior changes when the same task is described at different levels of detail. We introduce Mini-BEHAVIOR-Gran, a new benchmark for controlled studies of instruction granularity that extends Mini-BEHAVIOR with multiple instruction variants per task, ranging from high-level goal descriptions to step-by-step guidance. Using this benchmark, we compare four candidate metrics for cross-task granularity quantification: token count, entity count, action-verb count, and planning-width, and find that width correlates most consistently with agent performance. Using width to organize training and evaluation further reveals a non-monotonic U-shaped relationship between instruction granularity and performance, with peaks at both fine and coarse extremes. Further analysis suggests that the coarse-granularity performance rebound is associated with shallow grounding, where agents learn vision-dominant policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17019 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents Huang, Sukai Zhang, Chenyuan Ke, Fucai Cai, Zhixi Haffari, Gholamreza Qu, Lizhen Rezatofighi, Hamid Artificial Intelligence Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction, making it difficult to study how agent behavior changes when the same task is described at different levels of detail. We introduce Mini-BEHAVIOR-Gran, a new benchmark for controlled studies of instruction granularity that extends Mini-BEHAVIOR with multiple instruction variants per task, ranging from high-level goal descriptions to step-by-step guidance. Using this benchmark, we compare four candidate metrics for cross-task granularity quantification: token count, entity count, action-verb count, and planning-width, and find that width correlates most consistently with agent performance. Using width to organize training and evaluation further reveals a non-monotonic U-shaped relationship between instruction granularity and performance, with peaks at both fine and coarse extremes. Further analysis suggests that the coarse-granularity performance rebound is associated with shallow grounding, where agents learn vision-dominant policies. |
| title | Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17019 |