Creative Robot Tool Use by Counterfactual Reasoning

• URL: http://arxiv.org/abs/2605.05411v1
• Date: Wed, 06 May 2026 20:10:28 GMT
• Title: Creative Robot Tool Use by Counterfactual Reasoning
• Abstract summary: We propose a causal reasoning framework for creative robot tool use where a suitable tool for a task is correctly identified for use beyond its primary objectives.<n>We decouple the causal discovery problem into two complementary components: VLM-based feature suggestion and counterfactual tool generation.<n>By reconstructing the task in a dynamics model, our approach grounds tool use in the physics of the problem.
• Score: 12.0843035300871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a causal reasoning framework for creative robot tool use where a suitable tool for a task is correctly identified for use beyond its primary objectives. The proposed framework first discovers the causal relationships between the tool and the task by conducting simulated experiments in a dynamics model. We decouple the causal discovery problem into two complementary components: VLM-based feature suggestion and counterfactual tool generation via targeted geometric and physical feature perturbations. Then, novel objects are classified based on identified causal features, and the tool use skill is transferred via keypoint matching conditioned on the identified causal features. By reconstructing the task in a dynamics model, our approach grounds tool use in the physics of the problem. We illustrate our approach in reaching a distant object with different sticks, scooping candies from a bowl using diverse items, and using different boxes or crates as stepping platforms to retrieve an object from a high shelf. Our baseline comparisons show that identifying causal features and grounding them in physical tool properties leads to more reliable tool selection and stronger skill keypoint transfer.

Related papers

• Lomekwi: Resource-Bounded Tool Discovery in LLM Agents [2.06749085915751]
  We decompose tool use into curiosity, recognition, and efficiency.<n>We show that this framework can be applied to existing discovery tasks, such as Voyager.
  arXiv  Detail & Related papers  (2026-07-18T20:40:13Z)
• The Tool Illusion: Rethinking Tool Use in Web Agents [60.49303190288166]
  We revisit tool use in web agents through an extensive and carefully controlled study.<n>Our findings both revise some prior conclusions and complement others with broader evidence.
  arXiv  Detail & Related papers  (2026-04-03T21:18:26Z)
• AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning [66.24374176797075]
  We introduce textbfAdaReasoner, a family of multimodal models that learn tool use as a general reasoning skill rather than as tool-specific or explicitly supervised behavior.<n>AdaReasoner is enabled by (i) a scalable data curation pipeline exposing models to long-horizon, multi-step tool interactions; (ii) Tool-GRPO, a reinforcement learning algorithm that prioritizes tool selection and sequencing based on end-task success; and (iii) an adaptive learning mechanism that dynamically regulates tool usage.
  arXiv  Detail & Related papers  (2026-01-26T16:04:43Z)
• ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning [80.10274552177096]
  Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks.<n>The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools.<n>We propose a systematic approach to automatically an unstructured collection of tools into a structured tool library.
  arXiv  Detail & Related papers  (2025-10-09T04:11:16Z)
• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• Learning Generalizable Tool-use Skills through Trajectory Generation [13.879860388944214]
  We train a single model on four different deformable object manipulation tasks. The model generalizes to various novel tools, significantly outperforming baselines. We further test our trained policy in the real world with unseen tools, where it achieves the performance comparable to human.
  arXiv  Detail & Related papers  (2023-09-29T21:32:42Z)
• Tool Learning with Foundation Models [158.8640687353623]
  With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field.
  arXiv  Detail & Related papers  (2023-04-17T15:16:10Z)
• How to select and use tools? : Active Perception of Target Objects Using Multimodal Deep Learning [9.677391628613025]
  We focus on active perception using multimodal sensorimotor data while a robot interacts with objects. We construct a deep neural networks (DNN) model that learns to recognize object characteristics. We also examine the contributions of images, force, and tactile data and show that learning a variety of multimodal information results in rich perception for tool use.
  arXiv  Detail & Related papers  (2021-06-04T12:49:30Z)
• TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators [15.61285199988595]
  We introduce TANGO, a novel neural model for predicting task-specific tool interactions. TANGO encodes the world state comprising of objects and symbolic relationships between them using a graph neural network. We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments.
  arXiv  Detail & Related papers  (2021-05-05T18:11:57Z)
• Emergence of Different Modes of Tool Use in a Reaching and Dragging Task [7.40839907166763]
  In this paper, we investigate different modes of tool use that emerge in a reaching and dragging task. We trained a deep-reinforcement learning based controller with minimal reward shaping information to tackle this task. We observed the emergence of a wide range of unexpected behaviors, not directly encoded in the motor primitives or reward functions.
  arXiv  Detail & Related papers  (2020-12-08T19:37:58Z)
• Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment [73.9469267445146]
  First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor pose significant sample-efficiency challenges for reinforcement learning agents. We show that one can learn object-interaction tasks from scratch without supervision by learning an attentive object-model as an auxiliary task.
  arXiv  Detail & Related papers  (2020-10-28T19:27:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.