arXiv AI
EMHO: EMbodied Agent Harness Optimization via Experience Traces
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 14
EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
arXiv:2605. 10332v2 Announce Type: replace Abstract: Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments.
arXiv Computation and Language
1d ago
AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents
arXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy,...
arXiv AI
4d ago
EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
EmbodiedCLBench is the first benchmark designed to evaluate continual learning in embodied simulation environments, focusing on self‑evolving agents. The benchmark uses compositional generalization to test whether agents can learn basic tasks and then recombine those skills to solve more complex, unseen tasks. Experiments across various agent harnesses and learning methods reveal that while basic task experience improves performance on advanced tasks, this benefit does not scale with more learning samples and current agents fail to extract additional useful information.
arXiv AI
Jun 18
Guava: An Effective and Universal Harness for Embodied Manipulation
arXiv:2606. 18363v1 Announce Type: cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents.
arXiv AI
Sep 30
Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
arXiv:2606.18363v3 Announce Type: replace-cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through...
arXiv Machine Learning
Oct 7
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
arXiv:2608.05446v2 Announce Type: replace Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experie...