arXiv AI By Rajat Bhattacharjya, Hyeonjong Ju, Sing-Yao Wu, Eli Bozorgzadeh, Nikil Dutt

MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation

Read the original on arXiv AI →

arXiv:2607. 15589v1 Announce Type: cross Abstract: Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Aug 12

From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents

arXiv:2608. 10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes.

By Caili Yu, Yiqi Wang, Jiaqi Zhang, Yiqun Duan, Mingkai Zheng, Zhangkai Wu, Kaize Shi, Taotao Cai