arXiv (All)
open access
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker than these numbers suggest. We trace this illusion to a structural property we term low scene entropy: when a visual scene admits only one valid task, language becomes redundant and
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Action- and Language-Conditioned Video Assessment for Embodied Control#684576
- Action- and Language-Conditioned Video Assessment for Embodied Control#682800
- CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation#1105100
- Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models#1049387
- ActionGround: Training-Free Runtime Refinement of Frozen VLA Policies#1117968
Record · ID 1061273
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive