BrainMem equips LLM-based embodied planners with working, episodic, and semantic memory that evolves interaction histories into retrievable knowledge graphs and guidelines, raising success rates on long-horizon 3D benchmarks.
Transactions on Machine Learning Research (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Cognitive Agent Compilation uses a teacher LLM to create explicit, inspectable problem-solving agents by separating knowledge, policy, and verification components for educational applications.
citing papers explorer
-
BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
BrainMem equips LLM-based embodied planners with working, episodic, and semantic memory that evolves interaction histories into retrievable knowledge graphs and guidelines, raising success rates on long-horizon 3D benchmarks.
-
Cognitive Agent Compilation for Explicit Problem Solver Modeling
Cognitive Agent Compilation uses a teacher LLM to create explicit, inspectable problem-solving agents by separating knowledge, policy, and verification components for educational applications.