arXiv AI July 24, 2026 By Chaofan Pan, Lingfei Ren, Xiangyu Jiang, Yanhua Li, Xuemei Cao, Xiangkun Wang, Hao Yu, Wei Wei, Xin Yang

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

Read the original on arXiv AI →

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.

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 AI.

arXiv Machine Learning

Aug 3

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

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.

By Zihao Ding, Jun Huang, Liang Dong

agents multimodal

arXiv Machine Learning

Aug 24

Rethinking Demonstration Unlearning in Imitation Learning for Robotics

arXiv:2608.20784v1 Announce Type: cross Abstract: Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural...

By Jiazhuo Li, Yu Zhang, Yiming Fei, Kangkang Dong, Xiaojun Zhu, Houde Liu, Jinze Tao

robotics

arXiv AI

Jul 14

EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents

arXiv:2607. 09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments.

By Mianqiu Huang, Taofeng Xue, Chong Peng, Jinrui Ding, Sicheng Fan, Jiale Hong, Yufei Gao, Xiaocheng Zhang, Linsen Guo, Xin Yang, Dengchang Zhao, Yuchen Xie, Peng Pei, Xunliang Xie, Xipeng Qiu

agents reinforcement-learning multimodal

Hugging Face Trending Papers

Sep 23

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents

Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Existing compression strategies often score historic...

agents efficiency safety

arXiv AI

Sep 10

AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories

arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundam...

By Zhiyi Lyu, Yewen Li, Longtao Zheng, Shengtian Yang, Lang Feng, Lei Feng, Peng Jiang, Kun Gai, Qingpeng Cai, Bo An

llms agents

arXiv AI

Sep 24

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents

The paper introduces Direct Relational Set‑Risk Pruning (DRSR), a method for compressing the history of long‑horizon language‑model agents by selecting deletion sets based on risk constraints rather than independent unit scores. DRSR builds counterfactual supervision offline, then uses a lightweight scorer to predict set‑level harm during deployment, removing the largest safe set while respecting recency, protocol, and budget limits. Experiments on WorkBuddyBench Full260 and Eval40 show that DRSR improves mean reward from 0.699 to 0.802 and reduces token usage by over 20%, with further analyses highlighting the importance of decision‑conditioned relations, retained context, pair interactions, and abstention.

By Mingxuan Wang, Bo Wang, Fei Luo, Guorun Yao, Chao Ning, Yinglong Guo, Hongyue Chen, Yanbiao Ma, Jungong Han

agents efficiency safety

One email a morning, machine-written

Related stories

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

Rethinking Demonstration Unlearning in Imitation Learning for Robotics

EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents

AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents