VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation

Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded decisions that respect robot embodiment, workspace geometry, reachability, collision constraints, and grasp feasibility. This paper presents a hardware-aware large language model-vision-language model (LLM-VLM) manipulation framework for a simulated Franka Research 3 robot in NVIDIA Isaac Sim. The framework separates symbolic reasoning from metric execution: an API-hosted LLM planner receives a structured scene summary and generates only symbolic task information, including the object to manipulate, target relation, approach preference, and objects to avoid. A local Qwen3-VL 8B VLM verifier supports semantic confirmation of ambiguous objects and open-container surrogates. Both the LLM planner and the VLM verifier are prohibited from generating robot coordinates, grasp poses, keepout dimensions, gripper commands, trajectory waypoints, or success labels. Instead, these decisions are handled by deterministic grounding and execution modules that use the robot model, scene geometry, MoveIt 2 collision checking, inverse kinematics, grasp validation, release verification, and final visual assessment. Execution feedback is returned only as symbolic context for replanning. The framework is evaluated through simulated digital-twin trials involving pickup, occluded-source access, keepout reasoning, relation placement, and sequential manipulation tasks.

Vision-Language Models (VLMs) exhibit strong visual reasoning capabilities, yet they still struggle with 3D understanding. In particular, VLMs often fail to infer a text-consistent goal 6D pose of a target object in a 3D scene. However, we find that with some inference-time techniques and iterative reasoning, VLMs can achieve dramatic performance gains. Concretely, given a 3D scene represented by an RGB-D image (or a compositional scene of 3D meshes) and a text instruction specifying a desired state change, we repeat the following loop: observe the current scene; evaluate whether it is faithful to the instruction; propose a pose update for the target object; apply the update; and render the updated scene. Through this closed-loop interaction, the VLM effectively acts as an agent. We further introduce three inference-time techniques that are essential to this closed-loop process: (i) multi-view reasoning with supporting view selection, (ii) object-centered coordinate system visualization, and (iii) single-axis rotation prediction. Without any additional fine-tuning or new modules, our approach surpasses prior methods at predicting the text-guided goal 6D pose of the target object. It works consistently across both closed-source and open-source VLMs. Moreover, when combining our 6D pose prediction with simple robot motion planning, it enables more successful robot manipulation than recent Vision-Language-Action models (VLAs). Finally, we conduct an ablation study to demonstrate the necessity of each proposed technique.

Natural-language manipulation instructions specify the task goal but leave the underlying robot trajectory unspecified. We present AntiGrounding, a visual action-selection framework built around a dual geometric-visual trajectory interface. After feasibility filtering, each retained short trajectory is both an explicit motion plan for execution and a rendered prompt for instruction-conditioned vision-language model (VLM) evaluation. Structured multi-view visual question answering (VQA) scores safety, task alignment, efficiency, and physical plausibility; weighted view fusion aggregates the trajectory scores. These scores guide subsequent translational trajectory proposals; separate orientation and gripper controls coordinate interaction. An initialized digital twin provides the planning state and validates selected segments before the real robot executes the same waypoint sequences. Across eight real-world manipulation tasks, AntiGrounding with a single GPT-6 Astra evaluator achieves 71.25% overall success, compared with 50.00% for pi0.5 and 47.50% for a PIVOT-style visual proposal-selection baseline using the same evaluator under the reported deployment protocol. Component ablations and evaluator-sensitivity analyses examine trajectory evaluation, proposal search, orientation control, and evaluator choice. The interface connects general-purpose multimodal reasoning to executable trajectories, with performance bounded by digital-twin fidelity and physical interaction.