Metraipolis › archive › dc_cbc4cec57b23

A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory — arXiv:2611.02912

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02912
License (as archived)
CC0-1.0
Archived
2026-11-03T11:10:57.046Z
SHA-256 of the archived text
64795d6fd576a8d3d7a887937d60c69058aebe0be3ed3e42d582ffa988be8e00
Stable URL of this page
https://metraipolis.com/documento/dc_cbc4cec57b23

How to cite

A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory — arXiv:2611.02912 — arXiv (en), https://arxiv.org/abs/2611.02912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbc4cec57b23 (Metraipolis archive dc_cbc4cec57b23, sha256 64795d6fd576a8d3d7a887937d60c69058aebe0be3ed3e42d582ffa988be8e00)
BibTeX
@misc{dccbc4cec57b23,
  title = {A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory — arXiv:2611.02912},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02912},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbc4cec57b23; sha256 64795d6fd576a8d3d7a887937d60c69058aebe0be3ed3e42d582ffa988be8e00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.02912 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:59:52.355Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).