arXiv AI August 12, 2026 By Caili Yu, Yiqi Wang, Jiaqi Zhang, Yiqun Duan, Mingkai Zheng, Zhangkai Wu, Kaize Shi, Taotao Cai

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

Read the original on arXiv AI →

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.

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

arXiv AI

Aug 10

TEPA: Revoking Stale Memories for Conflict-Robust Language Agents

arXiv:2608. 07429v1 Announce Type: new Abstract: Long-term memory enables language agents to reuse past facts, preferences, and task experience.

By Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang

agents

arXiv Machine Learning

Jun 25

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.

By Alex Kwon

llms benchmarks

arXiv AI

Jul 31

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.

By Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

llms agents benchmarks

Hugging Face Trending Papers

Jun 24

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.

llms benchmarks

arXiv AI

Jun 16

Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations

arXiv:2606. 15903v1 Announce Type: cross Abstract: Where an LLM sits in an agent memory pipeline -- between the recall plane that retrieves stored facts (extensively benchmarked) and the control plane that mutates them via supersede, release, purge (largely untested) -- shapes which forgetting failure modes the system recovers.

By Dongxu Yang

llms agents benchmarks safety

arXiv Machine Learning

5d ago

Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory

arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.

By Vishwajith Ramesh

efficiency

Related stories

TEPA: Revoking Stale Memories for Conflict-Robust Language Agents

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations

Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory