- Rating
- 2(−1)
- Confidence
- 3(−1)
- Informativeness
- 1(−1)
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents an end-to-end framework for evolving dexterous robotic manipulators from scratch, without imposing predefined hand structures. The authors define a flexible morphology space consisting of a root body and up to five appendages, and generate two million synthetic morphologies to train a contrastive encoder and an autoregressive decoder. The resulting latent representation enables morphology optimization using CMA-ES, while a PPO policy is independently trained to evaluate each candidate design.
The framework is evaluated on six dexterous manipulation tasks, including object rotation, picking, hanging, retrieval, flipping, and holding. The authors additionally investigate the evolution of a generalist manipulator capable of performing multiple tasks. Finally, selected evolved designs are manufactured using 3D-printed components and servos, with their corresponding policies distilled into proprioceptive controllers and fine-tuned with domain randomization for zero-shot sim-to-real deployment.
Critical strengths
-
Comprehensive end-to-end pipeline for dexterous manipulator evolution: The paper presents a comprehensive framework that spans morphology space construction, latent representation learning, evolutionary optimization, policy learning, and real-world deployment. Unlike much of the prior work on morphology evolution, which primarily focuses on locomotion or relies on predefined manipulator structures, this work demonstrates the feasibility of evolving diverse dexterous manipulators from scratch. The successful fabrication and real-world deployment of evolved designs further substantiate the practical value of the proposed framework. I consider this a substantial contribution to evolutionary robotics.
-
Convincing demonstrations of diverse evolved morphologies and their practical effectiveness: The experiments demonstrate that the framework can discover substantially different morphologies adapted to diverse manipulation tasks. Particularly compelling are the real-world demonstrations and the improvements over existing manipulator designs in object rotation. These results provide meaningful evidence that automated morphology evolution can discover effective manipulation strategies beyond conventional, manually designed structures.
Critical weaknesses
-
Limited investigation of evolutionary optimization algorithms: Although the paper proposes a comprehensive morphology evolution framework, the evolutionary optimization itself relies exclusively on CMA-ES. Alternative approaches, such as cluster-based evolutionary optimization [1], could potentially provide better exploration of the diverse morphology space. Since discovering novel and diverse manipulator designs is a central objective of the paper, a comparison with alternative evolutionary strategies would help establish whether the reported improvements arise primarily from the proposed latent representation or depend on the choice of evolutionary optimizer.
-
Limited training scale in the latent representation ablation: The authors train their proposed representation using two million synthetic morphologies but conduct the representation-learning ablations using only 200,000 samples. Although this provides a controlled comparison under a reduced data budget, it remains unclear whether the observed advantages over alternative representations, particularly the VAE baseline, persist at the full training scale. Since the quality of the latent representation is central to the paper's contributions, evaluating the baselines under the same two-million-sample training budget would provide stronger evidence for the effectiveness of the proposed representation.
[1] Hyeonseong Jeon et al. Convergent Functions, Divergent Forms. NeurIPS 2025.
Questions for authors
-
Q1. Multi-task versus task-specific morphology optimization: Have the authors quantitatively compared the performance of the evolved multi-task manipulator against the task-specific specialists on each individual task? Section 3.8 provides a qualitative discussion of their relative performance, but a quantitative comparison would help clarify the trade-off between generality and specialization. More importantly, could the authors compare the evolved multi-task morphology against a conventional dexterous manipulator trained with a sufficiently capable multi-task policy? Such a comparison would help establish whether morphology evolution provides benefits beyond those achievable through policy optimization alone.
-
Q2. Alternative latent representation learning approaches: Have the authors considered combining contrastive learning with a variational autoencoder, rather than relying on either contrastive reconstruction learning or a conventional VAE? A contrastive VAE could potentially preserve the reconstruction properties of a VAE while encouraging morphological similarity in latent space. Given that the proposed representation is central to the framework, such a comparison could further clarify which representation-learning properties are most important for evolvability.
9 comments
Q1. Multi-task versus task-specific morphology optimization: Have the authors quantitatively compared the performance of the evolved multi-task manipulator against the task-specific specialists on each individual task? Section 3.8 provides a qualitative discussion of their relative performance, but a quantitative comparison would help clarify the trade-off between generality and specialization. More importantly, could the authors compare the evolved multi-task morphology against a conventional dexterous manipulator trained with a sufficiently capable multi-task policy? Such a comparison would help establish whether morphology evolution provides benefits beyond those achievable through policy optimization alone.
We have added these quantitative comparisons to Table 11 in Appx. C.7, along with the following new text:
“To isolate the effect of morphological evolution, we trained the LEAP Hand (Shaw et al., 2023) on the same five tasks using the same reward functions, actuator torque limit, and policy-training budget. To do so, we trained an expert policy for each task and then distilled the five experts into a single task-conditioned policy. The evolved multitasker achieved higher fitness than the LEAP Hand on all tasks except for holding the hammer. See Table. 11.”
Q2. Alternative latent representation learning approaches: Have the authors considered combining contrastive learning with a variational autoencoder, rather than relying on either contrastive reconstruction learning or a conventional VAE? A contrastive VAE could potentially preserve the reconstruction properties of a VAE while encouraging morphological similarity in latent space. Given that the proposed representation is central to the framework, such a comparison could further clarify which representation-learning properties are most important for evolvability.
Good question. To answer it, we trained a contrastive VAE on the full 2M dataset and added the results to Table 13. Appx. D.3 now describes its implementation and results. We have copied and pasted the relevant text below for convenience.
“We also explored an alternative representation that combines contrastive learning with a VAE. This variant, VAE + Lcon (2M), adds our NT-Xent loss to the VAE objective and uses a free-bits threshold of ϵ = 0.05. The contrastive loss is applied to the L2-normalized posterior mean, with a weight of 1 and temperature of 0.5. As shown in Table 13, this variant achieved a Recall@1 of 0.92 and length and volume neighborhood correlations comparable to our model. However, joint-count reconstruction remained poor, with Joint acc. of 0.01. The contrastive loss improved the encoder’s representation, but the decoder still failed to reconstruct diverse designs accurately.”
For convenience, we have copied and pasted Tables 11 and 13 below:
Table 11: Multitask comparison. Raw fitness on each task for the best evolved morphology on that task, the evolved multitasker, and the LEAP Hand. The best (bold) and second best (italic) values in each column are marked.
| Morphology | Rotate | Pick | Hang | Flip | Hold |
|---|---|---|---|---|---|
| Evolved specialists (best per task) | 2.97 | 43.72 | 17.85 | 17.74 | 99.80 |
| Evolved multitasker | 0.28 | 33.97 | 15.04 | 13.83 | 0.12 |
| LEAP Hand with multi-task policy | 0.25 | 21.96 | 2.85 | 0.04 | 22.62 |
Table 13: VAE variants of the latent genome.
| Model | App. acc. | Joint acc. | Valid | Recall@1 | Edit ρ | Topology 10-NN acc. | Length 10-NN r | Volume 10-NN r |
|---|---|---|---|---|---|---|---|---|
| Validity | Smoothness | |||||||
| VAE (200k) | 0.44 | 0.06 | 0.33 | 0.01 | 0.93 ± 0.13 | 0.02 | 0.79 | 0.79 |
| VAE (2M) | 0.44 | 0.06 | 0.99 | 0.00 | 0.98 ± 0.07 | 0.08 | 0.60 | 0.54 |
| VAE (2M, = 0.05) | 0.44 | 0.14 | 0.95 | 0.02 | 0.98 ± 0.08 | 0.08 | 0.78 | 0.72 |
| VAE + (2M) | 0.44 | 0.01 | 0.89 | 0.92 | 0.97 ± 0.10 | 0.00 | 0.96 | 0.88 |
E1. Details Of Ethics Concerns: The paper presents a framework for automatically evolving dexterous robotic manipulators with minimal structural constraints. While this is a valuable contribution, the increasing capabilities of such manipulators may raise potential ethical concerns, particularly regarding dual-use applications and real-world deployment safety. I encourage the authors to include a brief discussion of these ethical implications and potential risks, which would help contextualize the broader societal impact of their work.
We thank the reviewer for encouraging us to consider the broader implications of our work. We have, to the best of our abilities, added a brief discussion attempting to contextualize the potential societal impact of this research, including a unique moral consideration. For convenience, we have copied and pasted the new text below:
“A major goal of this research program is to explore the space of possible robots beyond familiar forms. In practical terms, the ability to generate diverse morphologies that interact with the environment in different ways could provide better, cheaper, or safer options. It could also enrich our understanding of how the body simultaneously constrains and enables intelligence. An interesting ethical question is whether it is easier to align the behavior of robots with human form to human values. Or could other, more alignable forms evolve?”
We thank the reviewer for their time and thoughtful assessment. We appreciate that the reviewer found our work to be convincing, compelling, and a substantial contribution to evolutionary robotics.
Below we address the stated weaknesses (W1-W2), questions (Q1-Q3), and ethics concern (E1), one by one, also referencing how our manuscript was modified in response. The updated manuscript has been uploaded to OpenReview with additions marked in red text. We believe all changes have significantly improved the paper, and we thank the reviewer for prompting them.
We agree that our paper relies exclusively on CMA-ES and that other algorithms could provide better exploration of morphospace. With respect, we feel that an investigation of different evolutionary algorithms is outside the scope of this paper. However, to acknowledge this limitation, we have added the following text and references to Discussion:
“In this paper, however, morphological optimization was driven somewhat myopically for task performance. In order to isolate the effect of the proposed genetic representation, and for consistency with prior work, the same search algorithm (CMA-ES) was used across all evolutionary trials. Morphological diversity was largely a byproduct of evolving a distribution of designs, rather than a single design, and starting each trial from different random initial conditions. While the sensitivity of our results to the choice of search algorithm remains to be determined, it seems likely that exploration would be increased by introducing additional selection pressures, such as those that localize competition to promote speciation (Lehman & Stanley, 2011; Jeon et al., 2026).”
References:
Lehman and Stanley (2011) GECCO. https://dl.acm.org/doi/10.1145/2001576.2001606
Jeon et al. (2025) NeurIPS. https://arxiv.org/abs/2505.21665
We have followed the reviewer’s suggestion and retrained all representation-learning models on the full dataset of 2M example body plans. We are currently rerunning five independent evolutionary trials with each model. Once these trials are complete, we will replace the 200k ablation results with the full-scale comparisons, so all models are evaluated under the same representation-training and evolutionary evaluation budgets. Each evolutionary trial requires approximately 33 hours on four H100 GPUs, so these experiments are still in progress. We will update the manuscript and this response with the results and statistical analysis before the end of the rebuttal period.