Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current execution context.
Existing memory systems primarily optimize construction and retrieval; semantic relevance and historical success therefore remain insufficient when retrieved experience contains incompatible actions or an inappropriate level of structure.
We introduce Memory Adaptation for Task-Conditioned Execution (MATE)
MATE re moves obsolete control context, extracts condition-action-effect transitions, applies verified action normalization, selects a task dependent representation, and serializes the result under a fixed budget without additional LLM inference.
On 134 ALFWorld tasks
MATE achieves task success rates of 81.3% and 93.3% with Qwen2.5-14B and 72B while using approximately one-tenth of the tokens required by raw trajectories.
Controlled comparisons show
Verified action normalization is the principal mechanism by which MATE restores the utility of retrieved experience, supporting memory adaptation as a distinct stage between retrieval and embodied execution.