Recent advancements in Vision-Language Models (VLMs) have demonstrated impressive capabilities in static visual recognition and high-level semantic reasoning. However, current embodied exploration paradigms still heavily rely on imitation learning from human-annotated trajectories, which severely limits agents' generalization ability. The key bottleneck of realizing general autonomous embodied agents lies in Generalizable Visually Grounded Exploration: the ability to operate novel devices without manuals or specific training by actively grounding abstract world knowledge into fine-grained visual affordances. Yet, existing benchmarks fail to evaluate this capability: they generally rely on explicit documents and annotated trajectories, neglecting the dynamic Hypothesis-Interaction-Refinement process essential for functional device operation. To bridge this gap, we introduce VGEBench, a comprehensive benchmark designed to evaluate the generalizable visually grounded exploration capabilities of VLMs. Unlike static datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling agents to achieve goals by active visual perception and feedback-driven correction. Experimental results demonstrate that existing VLMs face significant challenges in translating semantic knowledge into physical execution and maintaining long-horizon state tracking.
J. de Curtò, Dayani Plasencia, Diego Sánchez +1cs.RO cs.AI cs.CV
Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception. We investigate this with an input-ablation battery: blind-image controls, repeated identical inputs, lane-axis reflection, non-visual baselines, and pipeline-integrity checks. Across nine direct-action models, six structured local VLMs, and an exploratory VLM-MPC hierarchy, we analyse 32,874 scored calls over two embodiments and three simulators. The direct-control results are largely negative: a constant-SLOW policy outperforms a scripted geometric controller, several models are image-invariant or nearly constant, and models that recognize longitudinal hazards still fail to transform LEFT and RIGHT under reflection. No local VLM meets the joint longitudinal and lateral grounding criteria. However, an image-only deterministic positive control estimates the lead gap with 0.090 m MAE and exact mirror equivariance, confirming the stimuli carry sufficient visual information; the failures are modular, not universal. A post-hoc, leakage-controlled symmetry-consensus guardian selects two models from 16 calibration frames and freezes a 2-of-4 hazard vote across original and reflected views. On 272 held-out frames it reaches 0.954 balanced accuracy (episode-cluster bootstrap 95% CI [0.895,0.990]); nested leave-one-episode-out recovers the same pair and threshold in all 12 folds. Abstaining on ties raises committed balanced accuracy to 0.973 at 0.824 coverage. With deterministic perception retaining lateral authority, offline modular replay achieves 0.934 action agreement and exact mirror equivariance. These results support current VLMs as bounded, selective hazard assistants, not monolithic zero-shot controllers.
Adrian Szvoren, Dimitrios Kanoulas, Nilufer Tuptukcs.CV cs.RO
Vision-language-action (VLA) models enable robot navigation from natural language and visual goals, but remain susceptible to perceptual distractions and ambiguous scene interpretations. This paper presents the first empirical evaluation of visual grounding for VLA navigation policies. We propose a real-time segmentation-based grounding method that highlights traversable areas in green and non-traversable areas in red using SegFormer. Two variants are evaluated: observation-only segmentation and joint observation-goal augmentation. Using OmniVLA on the Grand Tour dataset, we show that visual grounding reduces the mean waypoint error by 27-44% at the farthest waypoint, depending on the instruction length. The benefits are greater for long instructions than for short instructions, and grounding provides little improvement for image goals. Normalized error analysis indicates that grounding primarily acts as a trajectory length regularizer, reducing the predicted path length by 30% without improving per-unit-distance reasoning. Our results indicate that visual grounding offers a simple, computationally inexpensive method to improve VLA navigation without model retraining, although it cannot compensate for missing training signals in out-of-distribution instructions.
Iok Tong Lei, QianZhi Li, Ying Jie Yap +5cs.RO cs.LG
Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures. We present ACE (Agentic Control for Embodied Manipulation), a zero-shot workflow reasoning framework for tabletop pick-and-place from natural language. Rather than relying on direct low-level action mapping, ACE combines agentic workflow reasoning with two robot-facing executable skills: a visual grounding interface and a reusable pick-and-place primitive. To bridge semantic reasoning and physical control, the active sub-goal is grounded into a mask-mediated vision-action interface. This unified mask specifies the target object and destination, is tracked over time, exposed for human verification, and ultimately passed to a task-agnostic downstream policy for execution. Crucially, ACE operates in a closed loop supported by a multi-timescale memory. After an action is executed, the system automatically verifies whether the intended sub-goal succeeded, using the outcome to advance, retry, repair, or replan. This enables online adaptation to user corrections, scene changes, and physical failures. We evaluate ACE on logically complex, long-horizon tasks, including zero-shot multi-step equation formation with number cubes and constraint-based object retrieval. ACE demonstrates task-level zero-shot generalization on novel semantic constraints and randomized tabletop scenes without task-specific retraining. Specifically, while standard end-to-end baselines struggle to complete these logically demanding tasks, ACE achieves a 50% success rate in equation formation and a 70% success rate in constraint retrieval. This contrast demonstrates that explicit workflow reasoning and mask-mediated control offer a robust, practical route toward adaptable robotic manipulation.
Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity references remain implicit and ambiguous. This may cause the reasoning process to decouple from visual evidence, entity references to drift across steps, and a causal disconnection between the reasoning trajectory and the final answer, with these problems further amplified in multi-view scenarios due to cross-view appearance changes. To address these issues, we propose Pinned Chain-of-Thought (PinCoT), a structured reasoning paradigm that pins every reasoning step to visual evidence. PinCoT introduces the concept of reasoning anchor, which binds each task-relevant entity to a structured visual anchor with entity name, unique identity, view index, and spatial grounding, enabling consistent entity tracking across reasoning steps and views. We build a fully automated data generation pipeline to construct PIN-170K, a high-quality PinCoT-formatted reasoning dataset. We then train RoboPIN through three-stage post-training that progressively injects embodied knowledge, structured reasoning ability, and process-supervised alignment, with rewards that directly constrain both anchor localization and identity consistency during reasoning. On 14 benchmarks covering embodied spatial reasoning, multi-view reasoning, and pointing, RoboPIN with only 4B parameters surpasses 7B level open-source embodied models on average, achieving a 12% average improvement over the strongest 7B baseline, Mimo-Embodied. Further analysis shows that PinCoT improves grounding accuracy and cross-step identity consistency, validating the effectiveness of process supervision.
Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.