TacEvo: Self-Evolving Architecture Discovery for Robotic Tactile Perception via LLM-Driven Quality-Diversity Search

• URL: http://arxiv.org/abs/2606.30109v1
• Date: Mon, 29 Jun 2026 10:45:01 GMT
• Title: TacEvo: Self-Evolving Architecture Discovery for Robotic Tactile Perception via LLM-Driven Quality-Diversity Search
• Abstract summary: Vision-based tactile sensing converts contact-induced surface deformation into images.<n>TacEvo is a self-evolving architecture discovery framework that improves network designs from downstream feedback.
• Score: 6.975054201075641
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vision-based tactile sensing converts contact-induced surface deformation into images, enabling robots to infer contact forces and fine surface textures that are not accessible through conventional vision alone. However, tactile images are sensor- and physics-specific, so effective architectures often require expert intuition and extensive manual iteration. Existing neural architecture search (NAS) pipelines can reduce this burden, but they are often computationally expensive and restricted to hand-designed search spaces, which limits architectural novelty and diversity. We introduce TacEvo, a self-evolving architecture discovery framework that improves network designs from downstream feedback. TacEvo uses an LLM to generate code-level mutations and crossovers, and a MAP-Elites quality-diversity loop that preserves diverse elite architectures while preferentially reusing prompts that consistently yield improvements. Exploration is guided by two behavioural descriptors, Architectural Diversity and Efficiency Ratio, which encourage coverage across structural variations and compute-size trade-offs. On ViTacTip force regression and grating classification, TacEvo achieves high autonomous generation reliability (96.0%/94.5% trainable) and improves best validation fitness over 20 generations by 56.1%/96.1%. In a 20-seed post-search high-fidelity evaluation, TacEvo matches the expert baseline on force prediction and outperforms it on fine-grained grating classification. These results suggest that LLM-driven self-evolving search constitutes a practical paradigm for AI-assisted scientific discovery in specialised robotic sensing.

Related papers

• Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions [59.49967357689445]
  Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies.<n>This study presents a complete open-source dilated real-based framework for the development and validation of deep learning models for affective touch recognition in soft interactive companions.
  arXiv  Detail & Related papers  (2026-04-16T10:20:05Z)
• AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design [5.793027603299694]
  AutoMS is a multi-agent neuro-symbolic framework that reformulates inverse design as an evolutionary search.<n>Our novel Simulation-Aware Evolutionary Search (SAES) addresses the "blindness" of traditional evolutionary strategies.<n>AutoMS achieves a state-of-the-art 83.8% success rate on 17 diverse cross-physics tasks.
  arXiv  Detail & Related papers  (2026-03-28T08:51:33Z)
• DASViT: Differentiable Architecture Search for Vision Transformer [8.839801565444775]
  We introduce Differentiable Architecture Search for Vision Transformer (DASViT)<n>DASViT bridges the gap in differentiable search for ViTs and uncovers novel designs.<n> Experiments show that DASViT delivers architectures that break traditional Transformer encoder designs, outperform ViT-B/16 on multiple datasets, and achieve superior efficiency with fewer parameters and FLOPs.
  arXiv  Detail & Related papers  (2025-07-17T12:48:00Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition [20.209756662832365]
  Differentiable Neural Architecture Search (DARTS) automates the manual process of architecture design with high search efficiency.<n>We propose EM-DARTS, a hierarchical differentiable architecture search algorithm to automatically design the DL architecture for eye movement recognition.<n>We show that EM-DARTS is capable of producing an optimal architecture that leads to state-of-the-art recognition performance.
  arXiv  Detail & Related papers  (2024-09-22T13:11:08Z)
• Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition [9.905155497581815]
  We introduce automated network search (NAS) algorithms to the field of eye movement recognition. Relax DARTS is an improvement of the Differentiable Architecture Search (DARTS) to realize more efficient network search and training. Relax DARTS exhibits adaptability to other multi-feature temporal classification tasks.
  arXiv  Detail & Related papers  (2024-09-18T02:37:04Z)
• FocusFormer: Focusing on What We Need via Architecture Sampler [45.150346855368]
  Vision Transformers (ViTs) have underpinned the recent breakthroughs in computer vision. One-shot neural architecture search decouples the supernet training and architecture specialization for diverse deployment scenarios. We devise a simple yet effective method, called FocusFormer, to bridge such a gap.
  arXiv  Detail & Related papers  (2022-08-23T10:42:56Z)
• D-DARTS: Distributed Differentiable Architecture Search [75.12821786565318]
  Differentiable ARchiTecture Search (DARTS) is one of the most trending Neural Architecture Search (NAS) methods. We propose D-DARTS, a novel solution that addresses this problem by nesting several neural networks at cell-level.
  arXiv  Detail & Related papers  (2021-08-20T09:07:01Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)
• AutoSpace: Neural Architecture Search with Less Human Interference [84.42680793945007]
  Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. We propose a novel differentiable evolutionary framework named AutoSpace, which evolves the search space to an optimal one. With the learned search space, the performance of recent NAS algorithms can be improved significantly compared with using previously manually designed spaces.
  arXiv  Detail & Related papers  (2021-03-22T13:28:56Z)
• Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction [64.03526633651218]
  Click-Through Rate (CTR) prediction is one of the most important machine learning tasks in recommender systems. We propose an automated interaction architecture discovering framework for CTR prediction named AutoCTR.
  arXiv  Detail & Related papers  (2020-06-29T04:33:01Z)

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.