arXiv cs.CL· Yiqi Wang, Tongyuan Zhao, Jiaqi Zhang, Yiqun Duan, Zhangkai Wu, Mingkai Zheng, Taotao Cai·· 11 小时前AI 评分38
StateGraph：面向长期智能体记忆的依赖感知状态修订
A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory
AI 导读
StateGraph 提出依赖感知状态修订方法，用反事实验证从交互历史中恢复状态依赖图，仅当严格依赖失效且无独立支持路径时才使依赖状态失效。在 50 个案例的 StateChangeBench 上，其 Impact-F1 在深度 1 比 CUPMem 复现高 6.9 个百分点，深度 3+ 高 26.0 个百分点。在公开长期记忆基准上，多数数据集点估计与基线相当或更高。
正文 · 原文
Abstract:Long-lived agents rely on persistent memory of users, tasks and decisions, and this memory must stay consistent with a world that keeps changing. When an upstream fact changes, however, memory systems can revise the contradicted memory itself while the beliefs, plans and actions derived from it remain accepted, even though they have lost their support. We therefore formulate dependency-aware state revision, which asks not only what changed but also which dependent states should no longer be trusted. To address it, StateGraph maintains an evolving state dependency graph whose edges are recovered from interaction histories. Its core design is counterfactual verification: each candidate edge is tested by asking whether the dependent state would survive the loss of its premise, which separates support dependence from semantic relatedness, and revision then invalidates a dependent state only when a strict dependency fails and no independent support path survives. To test this design, we introduce StateChangeBench, a controlled benchmark of 50 author-constructed cases annotated with cascade depth, hard negatives and action consequences. On it, StateGraph's Impact-F1 margin over a CUPMem reimplementation is 6.9 percentage points at depth 1 and 26.0 at depth 3+. On public long-term memory benchmarks, its point estimates are comparable to or higher than those of the evaluated baselines on most datasets. These results provide initial evidence that explicit dependency tracking can improve selective memory revision under changing conditions.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.02912 [cs.CL] |
| (or arXiv:2611.02912v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02912 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yiqi Wang [view email]
[v1]
Mon, 2 Nov 2026 10:44:02 UTC (1,503 KB)
来源：arXiv cs.CL · arxiv.org