arXiv:2608. 07537v1 Announce Type: cross Abstract: In this study, we propose a framework that incorporates subjective evaluations provided by a Vision-Language Model (VLM) into the fitness evaluation and selection processes of a genetic algorithm.
arXiv:2608.23100v1 Announce Type: cross Abstract: Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation with cross-generational morphological ev...
arXiv:2604. 24155v3 Announce Type: replace-cross Abstract: The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making?
The paper introduces MISCO, an evolutionary framework that uses deep generative models to design voxel-based soft robots (VSRs). MISCO combines an estimation-of-distribution algorithm with a variational autoencoder that includes multi-task learning, position awareness, and inter-voxel signaling to improve representation and sampling efficiency. The authors provide theoretical guarantees of asymptotic convergence to globally optimal designs and demonstrate through simulations that MISCO effectively navigates large design spaces, producing high-performing VSRs for various tasks while balancing efficiency and diversity.
The paper introduces Auto‑Robotist, a self‑evolving large language model (LLM) agent that transforms evolutionary robot design search traces into an explicit natural‑language skill library. Each skill records a structural archetype, evidence‑grounded rules, and supporting designs, enabling the agent to retrieve and condition LLM edits during search while still using a genetic algorithm for exploration. Experiments on seven EvoGym tasks show that Auto‑Robotist outperforms standard genetic algorithms, especially when transferring learned skills to larger design spaces.
arXiv:2606. 30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulation benchmarks.
arXiv:2604. 08780v2 Announce Type: replace-cross Abstract: World models promise a paradigm shift in robotics, where an agent learns the physics of its environment once and then acquires behaviors efficiently.
arXiv:2608. 03361v1 Announce Type: cross Abstract: AI systems based on Large Language Models (LLMs) have prompted fears that they may harbor hidden goals, seek to dominate or eliminate humanity, or even suffer as sentient beings.
The paper investigates whether artificial evolution can replicate biological neuromodulation and diverse neuron types in indirectly encoded substrates. Experiments show that neuromodulation alone cannot overcome a 75% performance ceiling on parity tasks, but combining neuromodulation with per‑task activation function selection allows a single evolving genotype to achieve 100% success across five tasks. This demonstrates that both neuromodulation and evolvable computational primitives are necessary for multi‑behavioral open‑ended evolution.
arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills...
RoboLDA is a Bayesian probabilistic model that learns a four‑level hierarchy—task, robot, organ, voxel—from existing high‑performing voxel‑based soft robot designs. By training with variational inference, it uncovers consistent, intuitive hierarchical patterns and can generate new robot morphologies that outperform evolutionary algorithms by an average of 106.4% without further optimization. The inferred organ structures also improve modular control policies, demonstrating the model’s utility for zero‑shot design and motion control.
The paper evaluates Vision Language Models (VLMs) on Visual Question Answering tasks where questions violate Grice's maxims. By generating question modifiers that add non-essential, ambiguous, or false information, the authors show that VLMs such as ChatGPT, Claude, Gemini, and Llava exhibit reduced performance. They also compare human pragmatic reasoning to VLM reasoning, noting differences in how each handles human‑induced versus AI‑generated violations, and find that humans spend less time resolving VLM‑induced violations while VLMs are less accurate in those cases.
arXiv:2607. 22832v1 Announce Type: new Abstract: Long-horizon embodied tasks require policies that execute many dependent actions before task success can be observed.