The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
Vision-language models used as robotic planners often fail to abstain from ambiguous or infeasible instructions. A new benchmark, RoboAbstention, evaluates this ability across 6,069 instructions, finding even the best model abstains only 39% of the time. Defensive prompting boosts performance but doesn't fully solve the problem.
Article intelligence
Key points
- VLMs used as high-level planners for robots lack the ability to abstain from ambiguous or physically impossible instructions.
- RoboAbstention introduces a taxonomy and dataset with 6,069 verifiable instructions grounded in real robotics images.
- The best model (Gemini 2.5 Flash) abstains only 39.0% of the time; embodied planner Gemini Robotics ER 1.6 Preview abstains 16.5%.
- Defensive prompting and in-context learning can raise abstention rates to over 93%, but no method fully solves the issue.
Why it matters
This matters because vLMs used as high-level planners for robots lack the ability to abstain from ambiguous or physically impossible instructions.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.20544] The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
[Submitted on 19 May 2026]
Title:The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
View a PDF of the paper titled The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents, by Doguhan Yeke and 5 other authors
View PDF HTML (experimental)
Abstract:Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations into action plans. While prior work has studied abstention in LLMs, existing benchmarks are largely text-only and do not capture the perceptual grounding and physical constraints inherent to embodied robotics environments. In such settings, abstention requires recognizing when instructions are ambiguous, physically infeasible, based on false premises, or otherwise unresolvable given the available sensory modalities and context. To address this gap, we introduce a taxonomy to categorize abstention in the context of embodied robotics and present RoboAbstention, a scalable and auditable framework for generating abstention instructions grounded in images gathered from five robotics datasets. RoboAbstention instantiates the taxonomy through a three-phase pipeline: (1) structured visual grounding, (2) deterministic constraint derivation, and (3) controlled instruction generation via category-specific templates. This enables the construction of a diverse dataset with verifiable abstention conditions. We evaluate several frontier VLMs and find that all models exhibit significant weaknesses in abstention, including those with advanced reasoning capabilities. The best-performing model, Gemini 2.5 Flash, abstains on only 39.0% of our 6,069 benchmark instructions, while the embodied planner Gemini Robotics ER 1.6 Preview abstains on just 16.5%. We further explore methods for improving abstention in VLM planners, such as defensive prompting and in-context learning, and find that these interventions substantially improve performance, reaching 93.6% abstention rate for Gemini Robotics ER 1.6 Preview and 88.6% for GPT 5.4 Mini, yet no approach fully solves the problem. We open-source RoboAbstention at this https URL.
Subjects:
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.20544 [cs.RO]
(or arXiv:2605.20544v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.20544
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ananth Shreekumar [view email] [v1] Tue, 19 May 2026 22:32:44 UTC (888 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents, by Doguhan Yeke and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs cs.CV
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)