# TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation

arXiv: https://arxiv.org/abs/2606.11637 · HTML: https://mlsanity.com/paper/2606.11637/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 14 of 14)

- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [A Survey of Vision-Language Pre-Trained Models](https://mlsanity.com/paper/2202.10936/) (2022)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [Octopi: Object Property Reasoning with Large Tactile-Language Models](https://mlsanity.com/paper/2405.02794/) (2024)
- [AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors](https://mlsanity.com/paper/2502.12191/) (2025)
- [Transferable Tactile Transformers for Representation Learning Across Diverse Sensors and Tasks](https://mlsanity.com/paper/2406.13640/) (2024)
- [OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation](https://mlsanity.com/paper/2603.19201/) (2026)
- [Surveying the MLLM Landscape: A Meta-Review of Current Surveys](https://mlsanity.com/paper/2409.18991/) (2024)
- [Demonstrating the Octopi-1.5 Visual-Tactile-Language Model](https://mlsanity.com/paper/2507.09985/) (2025)
- [HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System](https://mlsanity.com/paper/2603.14807/) (2026)
- [Dual-Anchoring: Addressing State Drift in Vision-Language Navigation](https://mlsanity.com/paper/2604.17473/) (2026)
- [A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook](https://mlsanity.com/paper/2605.20266/) (2026)

## Built on by (most cited first, 2 of 2)

- [TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios](https://mlsanity.com/paper/2607.05131/) (2026)
- [VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios](https://mlsanity.com/paper/2607.14728/) (2026)

## Abstract (arXiv)

Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language systems for tactile commonsense reasoning, scaling such systems to realistic open-world settings remains challenging due to two key bottlenecks: (1) current tactile reasoning datasets remain limited in format and scale, providing insufficient supervision for reasoning from tactile observations to physical commonsense and hindering the learning of transferable tactile commonsense; (2) tactile signals are inherently redundant and action-specific, yet existing methods often overlook these properties, resulting in inefficient representations with limited semantic expressiveness. To address these limitations, we propose TouchThinker, a tactile-language framework that scales tactile commonsense reasoning to the open world from both data and representation perspectives. First, we construct TouchThinker-1M, a million-scale, multi-source tactile reasoning dataset covering 415 objects, 8 scenarios, and 7 sensor types, providing a solid data foundation for open-world generalization. We further introduce TouchThinker-Bench, an open-world benchmark with more realistic and diverse tasks. Then, we propose action-aware modeling mechanism to improve tactile representation efficiency and enable efficient reasoning. Experimental results demonstrate that TouchThinker achieves competitive performance against state-of-the-art models across multiple datasets. Our code and dataset will be made available at: https://github.com/lvkailin0118/TouchThinker.