arXiv Machine Learning August 3, 2026 By Zihao Ding, Jun Huang, Liang Dong

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

Read the original on arXiv Machine Learning →

arXiv:2607. 28829v1 Announce Type: cross 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 4

\textsc{Lethe}: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning

arXiv:2601. 22601v3 Announce Type: replace Abstract: Federated unlearning (FU) aims to erase knowledge from a global model.

By Wentai Wu, Hanwei Tan, Yijun Quan, Haixia Peng, Ligang He, Bin Yang, C. L. Philip Chen

nlp benchmarks

arXiv Machine Learning

Jun 3

Lethe: Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning

arXiv:2601. 22601v2 Announce Type: replace Abstract: Federated unlearning (FU) aims to erase designated client-level, class-level, or sample-level knowledge from a global model.

By Hanwei Tan, Wentai Wu, Ligang He, Yijun Quan

Hugging Face Trending Papers

Aug 4

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which gives rise to two challenges.

llms

arXiv AI

Aug 5

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

arXiv:2608. 03123v1 Announce Type: cross Abstract: Machine unlearning aims to eliminate the influence of sensitive data on a model.

By Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Haoran Luo, Jiapu Wang, Qing Yang, Jingwei Zhang

llms

arXiv AI

Sep 7

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.

By Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He

llms agents efficiency

arXiv AI

Jul 24

TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning

arXiv:2607. 21111v1 Announce Type: cross Abstract: Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after training.

By Chaofan Pan, Lingfei Ren, Xiangyu Jiang, Yanhua Li, Xuemei Cao, Xiangkun Wang, Hao Yu, Wei Wei, Xin Yang

agents reinforcement-learning robotics fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

\textsc{Lethe}: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning

Lethe: Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning