智能体
arxiv.org ·
新鲜记忆，陈旧计划：分布式 LLM 智能体记忆的推导时效性
论文指出，通过共享记忆继承计划的 LLM 智能体可能持有最新需求却执行基于旧输入推导的计划，即“记忆新、计划旧”。现有新鲜度检查比较本地副本与当前状态（观察时效性），而非计划所依赖的输入（推导时效性），因而漏检该失效。作者提出 Planfence：存储的计划携带其记录输入的精确链接，受保护动作执行前沿链接追踪到动作相关的依赖边界，向各输入所有者查询当前版本，刷新变更内容，并允许一次重规划后再阻断；应用代码提供链接并声明范围，无需共享记忆服务。实验显示，在固定原生 S-Bus 校验器时，提供继承输入版本可将检测到的交接冲突从 0/30 提升至 30/30；在 30 个插入规划后修订的五智能体实时工作流中，仅做新鲜度检查的执行器每次都执行陈旧计划，而 Planfence 与需共享存储的集中式血缘基线均 30/30 正确。在模拟 LTE 轨迹的匹配回放中，Planfence 每动作停顿为 143–237ms（更新率跨 64 倍范围），而每次更新同步耗时从 52ms 增至 1196ms，仅在最低测试更新率下同步更便宜；将查询限定到声明的依赖后，流量为每动作 8.1KiB，为 128 键全键校验的十分之一，全范围时两者持平。
AI推荐理由 arXiv 论文（v2，2026-09-27 修订），提出分布式 LLM 智能体记忆中的“推导时效性（derivation currency）”概念与 Planfence 机制，针对“记忆新、计划旧”的失效模式。摘要给出具体实验证据：在 30 个五智能体工作流中，仅做新鲜度检查的执行器每次都按陈旧计划行动，而 Planfence 与需共享存储的集中式血缘基线均 30/30 正确；在模拟 LTE 轨迹下停顿为每动作 143–237ms，依赖范围限定后流量为 8.1KiB/动作。局限在于实验规模较小（30 次）、依赖模拟网络轨迹，且需应用代码提供链接与声明范围，尚无生产环境验证。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.03340 (cs)
[Submitted on 3 Sep 2026 (v1), last revised 27 Sep 2026 (this version, v2)]
Title:Fresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory
Authors:Evan Chen, Shiqiang Wang, Christopher G. Brinton
View a PDF of the paper titled Fresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory, by Evan Chen and 2 other authors
View PDF
HTML (experimental)
Abstract:A large language model (LLM) agent that inherits a plan through shared memory can hold the latest requirement yet act on a plan derived from an older one: fresh memory, stale plan. Freshness checks miss this failure because they compare local copies with current state (observation currency) rather than the inputs the plan was derived from (derivation currency). Planfence makes derivation currency checkable after a handoff. Stored plans carry exact links to their recorded inputs; before a protected action, Planfence follows those links to an action-specific dependency frontier, asks each input's owner for its current head, refreshes what changed, and allows one replan before blocking. Application code supplies the links and declares the scope; no shared memory service is required. Holding the native S-Bus validator fixed, supplying inherited input versions raises detected handoff conflicts from 0/30 to 30/30: retained evidence is the missing ingredient. In 30 live five-agent workflows with a revision inserted after planning, a freshness-only executor acts on the stale plan every time, whereas Planfence, like a centralized-lineage baseline that requires a shared store, completes all 30 correctly. In matched replay under emulated LTE traces, Planfence's stall stays within 143-237ms per action across a 64$\times$ range of update rates while per-update synchronization grows from 52 to 1196ms; synchronization is cheaper only at the lowest tested rates. Scoping queries to the declared dependencies holds traffic at 8.1KiB per action, a tenth of all-key validation at 128 keys; at full scope the two tie.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.03340 [cs.AI]
(or
arXiv:2609.03340v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.03340
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Evan Chen [view email]
[v1]
Thu, 3 Sep 2026 03:56:15 UTC (516 KB)
[v2]
Sun, 27 Sep 2026 20:39:32 UTC (1,016 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Fresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory, by Evan Chen and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)