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: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,...
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:2606. 18363v1 Announce Type: cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents.
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: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...
arXiv:2607. 26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions.
arXiv:2608. 08523v1 Announce Type: new Abstract: Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction history into closed-loop decision making.
arXiv:2610.17089v1 Announce Type: cross Abstract: Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may requ...
arXiv:2606. 30111v2 Announce Type: replace-cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv:2605.24539v2 Announce Type: replace Abstract: Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior....
arXiv:2609.28236v1 Announce Type: new Abstract: Long-horizon embodied interaction requires agents to retain and continually update information about the environment as they observe, act, and encounte...