MutMem‑V2 builds on the original MutMem‑V1 by providing a complete portable verification contract and a clean‑install reproduction path for persistent agent memory. It defines exact canonical bytes, domain‑separated commitments, mandatory recall‑evidence, and other security primitives, and releases a protocol with 18 object schemas, 39 recall vectors, 15 mutation vectors, and 37 closed recall failure reasons. Independent Node and Python implementations agree on all 72 structural and cryptographic terminals, and a production‑conformance corpus confirms 42/42 cases across 28 required classes, demonstrating reproducible evidence and portable integrity under stated assumptions.
By Walid Saidi
arXiv:2608. 02843v1 Announce Type: cross Abstract: Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering.
By Walid Saidi
arXiv:2604. 16548v2 Announce Type: replace-cross Abstract: The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness, and propagation.
By Zehao Lin, Xixuan Hao, Renyu Fu, Shaobo Cui, Kai Chen, Chunyu Li, Zhiyu Li, Feiyu Xiong
arXiv:2609. 00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior.
By Zhenyu Zhao (Independent Researcher), Roy Zhao (Paul G. Allen School of Computer Science & Engineering, University of Washington)
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
arXiv:2607. 23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects.
By Xiaoyang Li, Yiqi Wang, Haohui Lu, Zhi Chen, Mo Li, Pingan Song, Taotao Cai
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
arXiv:2609.22243v1 Announce Type: new
Abstract: Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity...
By Xianliang Zeng, Zhanzhan Zhao
arXiv:2606. 01138v2 Announce Type: replace-cross Abstract: Agent-memory frameworks -- mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor -- each ship their own SDK, storage layout, and operational vocabulary.
By Thamilvendhan Munirathinam
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
The paper introduces PACE (Policy‑Attested Contract Execution), a framework that sits between large‑language‑model (LLM) based autonomous AI agents and on‑chain DeFi operations. PACE defines typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind an approved intent, policy, and simulation report to the exact on‑chain execution bytes, providing replay and expiration protection. In evaluations across 40 tasks and six baselines, PACE achieves zero unsafe executions and zero false positives, outperforming unguarded agents by a large margin.
By Rabimba Karanjai (Larry), Yang Lu (Larry), Richard Williamson (Larry), Hemanth Hm (Larry), Prakhar Mehrotra (Larry), Lei Xu (Larry), Weidong (Larry), Shi
Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions. We treat them as persistent-state systems: the operative system includes retrievable memories, but also task ledgers, permissions, credentials, commitments, provenance and audit records, shared state, trigger conditions, and externally committed effects linked to those records.