When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks

2026-07-30

AI Summary

This work addresses the challenge of reliable data forgetting in continually self-improving federated agent networks, where deleted data can induce “influence echoes” through subsequently retained trajectories, thereby undermining conventional unlearning mechanisms. The study is the first to formally identify and quantify this phenomenon and introduces MUTE, a systematic solution that leverages a lightweight server-side ledger to orchestrate forgetting-aware gradient updates, isolate and downweight high-influence trajectories, and enforce uplink budget constraints. Experimental results on the LIBERO benchmark and Jetson edge platforms demonstrate that MUTE effectively suppresses behavioral leakage and influence regeneration while preserving task performance, achieving significantly lower communication overhead compared to full retraining.

Abstract

Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back into later rounds. This closed loop makes unlearning harder than a one-time model repair. When a data owner requests deletion, the target data may have already shaped later retained trajectories, so retraining or model-side unlearning can leave an influence echo that returns as the network continues to operate. We show that this echo survives retained-data retraining, grows with the amount of forget-shaped retained data, and can be traced from deployment, collection, and aggregation records. To address this problem, we propose MUTE, a Muting Unlearned Trajectories' Echoes method for reliable deletion in self-improving federated agent networks. MUTE estimates downstream influence from a lightweight server ledger, removes the current residue through a forget-retain update, contains high-influence retained trajectories through quarantine or down-weighting, and audits later behavior to schedule additional erasure under an uplink budget. Experiments on LIBERO with two vision-language-action backbones, three deletion granularities, and a physical Jetson-based edge testbed show that MUTE keeps behavioral leakage and influence regeneration low while preserving task utility and using much less communication than full retraining.

Problem

• unlearning
• data deletion
• federated agent networks
• influence echo
• self-improving systems

Innovation

• federated unlearning
• influence echo
• MUTE
• self-improving agent networks
• data deletion