Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

Computer Science > Artificial Intelligence [Submitted on 12 May 2026] Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents Nishad Singhi, Christian Bialas, Snehal Jauhri, Vignesh Prasad, Georgia Chalvatzaki, Marcus Rohrbach, Anna Rohrbach Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models (MLLMs) have significantly advanced the reasoning capabilities of such agents through strong vision-language knowledge and chain-of-thought (CoT) reasoning, yet remain brittle when faced with challenging out-of-distribution scenarios. To address this, we propose Verifier-Guided Action Selection (VegAS), a test-time framework designed to improve the robustness of MLLM-based embodied agents through an explicit verification step. At inference time, rather than committing to a single decoded action, VeGAS samples an ensemble of candidate actions and uses a generative verifier to identify the most reliable choice, without modifying the underlying policy. Crucially, we find that using an MLLM off-the-shelf as a verifier yields no improvement, motivating our LLM-driven data synthesis strategy, which automatically constructs a diverse curriculum of failure cases to expose the verifier to a rich distribution of potential errors at training time. Across embodied reasoning benchmarks spanning the Habitat and ALFRED environments, VeGAS consistently improves generalization, achieving up to a 36% relative performance gain over strong CoT baselines on the most challenging multi-object, long-horizon tasks. Comments: CVPR 2026 (Findings) Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2605.12620 [cs.AI]   (or arXiv:2605.12620v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.12620 Focus to learn more Submission history From: Nishad Singhi [view email] [v1] Tue, 12 May 2026 18:08:24 UTC (3,261 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)