EvolvingAgent autonomously completes long-horizon tasks via a closed-loop planner-controller-reflector system with continual world model updates, reporting 111.74% higher success rates than baselines in Minecraft and human-level Atari performance.
Detach: Cross-domain learning for long-horizon tasks via mixture of disentangled experts.arXiv preprint arXiv:2508.07842
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
EvolvingAgent autonomously completes long-horizon tasks via a closed-loop planner-controller-reflector system with continual world model updates, reporting 111.74% higher success rates than baselines in Minecraft and human-level Atari performance.