FedRuleMem: Federated Memory for LLM Agents via Executable Rules

Large Language Model (LLM) agents typically remember experience through episodic replay or retrieval-augmented prompting. These mechanisms increase inference cost and expose detailed interaction records when shared across users. We propose FedRuleMem, a federated agent-memory system that shares executable rules: compact, stateless programs that check candidate actions and return corrective feedback. Clients synthesize rules from local failures, verify their behavior, and apply Minimum Description Length (MDL) pruning before upload. The server deduplicates retained rules and broadcasts a global library, which clients re-validate against subsequent local evidence. Raw interaction records remain local, and the acting LLM stays frozen, enabling black-box use. Across nine independent end-to-end runs on Crafter and ALFWorld, FedRuleMem reaches a Crafter Score of $13.5\pm 2.4$ and ALFWorld success of $64.8\pm 0.8\%$, outperforming the matched federated textual-rule control ($11.4\pm 2.0$ and $62.4\pm 0.9\%$). On Crafter, the final library occupies $0.031$ MB per client, and end-to-end token use is $61.9$k per task. These results support executable rules as compact shared memory for action correction across clients.