Metraipolis › archive › dc_7c73a22bd1fb
Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory — arXiv:2610.19474
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19474
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:01:41.058Z
- SHA-256 of the archived text
0831fdd2456b8e0c3ecaf52a27f8a18cb0c9389fe8b8e39f4eb207ad3cd3d314- Stable URL of this page
https://metraipolis.com/documento/dc_7c73a22bd1fb
How to cite
Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory — arXiv:2610.19474 — arXiv (en), https://arxiv.org/abs/2610.19474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c73a22bd1fb (Metraipolis archive dc_7c73a22bd1fb, sha256 0831fdd2456b8e0c3ecaf52a27f8a18cb0c9389fe8b8e39f4eb207ad3cd3d314)
BibTeX
@misc{dc7c73a22bd1fb,
title = {Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory — arXiv:2610.19474},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19474},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c73a22bd1fb; sha256 0831fdd2456b8e0c3ecaf52a27f8a18cb0c9389fe8b8e39f4eb207ad3cd3d314},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Questions about an agent's history often require aggregating events, which retrieval alone does not resolve. We combine source-preserving evidence access with executable aggregation. Trajectory Memory (TM) retains the original trajectory and constructs a source-addressable reading view at question time. TallyMem augments it with a reusable event ledger, model-generated event specifications and deterministic execution. With a commit-specific adaptation on 776 questions from 99 held-out MINTEval repositories, TallyMem raises Qwen3-32B exact match from 35.2% to 49.0%, a 13.8-point gain over TM; gains span 12.8-13.9 points across three readers. A controlled probe with event sets parsed independently from raw logs shows an 11.0-point gain, from 82.8% to 93.8%, without routing. On full AMA-Bench, the routed system yields a smaller 1.3-point gain, from 69.8% to 71.1%. These results support executable aggregation on tasks that require combining events, with benefits dependent on the task and event specification, the largest residual system-error category in our diagnostic analysis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19474 — 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 2026-10-15T19:35:48.239Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).