Metraipolis › archive › dc_d84ab380df20
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents — arXiv:2608.10502
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:26.745Z
- SHA-256 of the archived text
a6b9cbb6c013da0e976fc1c28ccd212f3fb36b0d1b97f54fcf58f1efb13c50c9- Stable URL of this page
https://metraipolis.com/documento/dc_d84ab380df20
How to cite
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents — arXiv:2608.10502 — arXiv (en), https://arxiv.org/abs/2608.10502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d84ab380df20 (Metraipolis archive dc_d84ab380df20, sha256 a6b9cbb6c013da0e976fc1c28ccd212f3fb36b0d1b97f54fcf58f1efb13c50c9)
BibTeX
@misc{dcd84ab380df20,
title = {From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents — arXiv:2608.10502},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d84ab380df20; sha256 a6b9cbb6c013da0e976fc1c28ccd212f3fb36b0d1b97f54fcf58f1efb13c50c9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes. Existing defenses mainly detect or delete suspicious memories, or revise the current response. Deleting the source leaves already propagated claims, actions, and derived memories active, whereas resetting the store or replaying the full trace destroys benign state and repeats unnecessary computation. We therefore formulate \textbf{post-failure memory recovery: } \textit{given a failed execution and diagnosed faulty memories, recover both the answer and persistent state while retaining unaffected work.} Our \textbf{dependency-guided rollback repair} builds a typed memory-to-action graph from runtime provenance, traces explicit downstream dependencies, preserves candidates with independent trusted support, deactivates unsupported memory state, and selectively replays only answer-relevant affected computation. We evaluate this approach on a 150-case controlled benchmark spanning three tool-use domains and four memory failure types, and on a 50-case trajectory-derived stress test adapted from LongMemEval-V2. On the controlled benchmark, it achieves 85.3\% recovery versus 77.3\% for the best competing recovery method, removes all diagnosed faulty memories, preserves all benign memories, and requires only selective replay with modest LLM-call cost. On the adapted subset, it reaches 68.0\% recovery versus 54.0\% for the next best method, while also achieving the highest claim invalidation F1, 0.669 versus 0.603. Overall, the results do not imply uniformly better trace reconstruction, but show that dependency-guided rollback repair provides a strong recovery--cost trade-off while repairing faulty memory state and preserving benign memory.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.10502 — 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 2026-10-19T05:57:28.275Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).