arXiv AI
Jun 2
Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
arXiv:2606. 00702v1 Announce Type: cross Abstract: We propose to turn generalist multi-embodiment value functions into reusable models for robot design.
Debate2Create: Robot Co-design via Multi-Agent LLM Debate
arXiv:2510. 25850v3 Announce Type: replace-cross Abstract: We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation.
Related stories
arXiv Machine Learning
Jun 11
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
arXiv:2606. 11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy.
arXiv AI
Jun 12
From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence
arXiv:2601. 21570v2 Announce Type: replace Abstract: The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection.
arXiv AI
Sep 25
When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills
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 AI
Sep 21
SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
SynthDemo‑RL introduces a teacher‑student framework that uses an automated teacher to generate successful manipulation trajectories from simulator‑privileged state, which are then distilled into a Vision‑Language‑Action (VLA) student via supervised fine‑tuning. The student is further refined with PPO using binary task‑success rewards. On the LIBERO‑PRO benchmark, SynthDemo‑RL rescues all 27 previously unsolvable tasks and achieves near‑perfect success rates, matching performance that would otherwise require human demonstrations.
arXiv AI
Sep 4
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
CORAL is a framework that enables autonomous multi‑agent evolution for open‑ended discovery, replacing rigid heuristics with long‑running agents that explore, reflect, and collaborate via shared memory and asynchronous execution. It incorporates safeguards such as isolated workspaces, evaluator separation, and resource management. In experiments across mathematical, algorithmic, and systems optimization tasks, CORAL achieves 3–10 times higher improvement rates with fewer evaluations than traditional evolutionary baselines, and improves the best known score on Anthropic’s kernel engineering task from 1363 to 1103 cycles.
arXiv AI
2d ago
PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
arXiv:2610.01260v1 Announce Type: cross Abstract: Quadrupedal locomotion requires balancing conflicting objectives such as command tracking, stability, and energy efficiency, yet conventional reinfor...
arXiv AI
4d ago
Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning
arXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLA...
arXiv AI
Sep 7
A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning
The paper presents a decentralized navigation framework for composite heterogeneous robots that integrates a large language model (LLM) policy agent, an Upper Confidence Bound (UCB) bandit, and a Double Deep Q-Network (Double DQN) controller. Each robot independently generates and refines policies at the round level using LLM inference, while the Double DQN handles tick-level action selection based on navigation variables and LLM priors. Across 30 rounds, the full configuration achieved all goals with the lowest median completion time (42 ticks) and a 25–39% improvement over other setups.
arXiv AI
Jun 26
EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning
arXiv:2606. 26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed.
arXiv AI
2d ago
HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution
arXiv:2610.02089v1 Announce Type: cross Abstract: As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use re...
arXiv AI
4d ago
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
arXiv:2609.37810v1 Announce Type: cross Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains chal...