Skip to content

[new-research] arXiv:2609.04875 — Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agent #77

Description

@github-actions

New arXiv Research Paper

arXiv ID: 2609.04875
Title: Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
Authors: Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He
Published: 2026-09-04T08:31:40Z
URL: https://arxiv.org/abs/2609.04875

Abstract (first 300 chars)

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. Yet today's "forget" operations delete a plaintext memory record and stop, leaving every artifact derived from the revoked in…

Suggested OWASP Mapping

ASI06, ASI01, ASI02, LLM02, DSGAI01

Suggested Action

Review this paper against the OWASP GenAI Crosswalk entries and update relevant mapping files if new attack patterns or mitigations are identified.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions