Metraipolis › archive › dc_d36aaa221166
ImplicitHop: Evaluating knowledge integration across context and memory — arXiv:2610.41169
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41169
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:43:05.665Z
- SHA-256 of the archived text
d26173c8e5b22c6a0bd7649b3305337488b1f3ac0c30ceeb1825d1afedcce022- Stable URL of this page
https://metraipolis.com/documento/dc_d36aaa221166
How to cite
ImplicitHop: Evaluating knowledge integration across context and memory — arXiv:2610.41169 — arXiv (en), https://arxiv.org/abs/2610.41169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d36aaa221166 (Metraipolis archive dc_d36aaa221166, sha256 d26173c8e5b22c6a0bd7649b3305337488b1f3ac0c30ceeb1825d1afedcce022)
BibTeX
@misc{dcd36aaa221166,
title = {ImplicitHop: Evaluating knowledge integration across context and memory — arXiv:2610.41169},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41169},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d36aaa221166; sha256 d26173c8e5b22c6a0bd7649b3305337488b1f3ac0c30ceeb1825d1afedcce022},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLMs). Whether information arrives during training or in-context, models must not only store local facts, but propagate their long-range implications globally. To explore information integration in LLMs, we introduce two complementary natural language benchmarks for large-scale evaluation of deductive reasoning as a function of inference depth. The first is a formal graph benchmark enabling controlled evaluation over a wide range of graph topologies and integration tasks; the second is a knowledge composition benchmark grounded in real-world knowledge graphs. We use these benchmarks to compare knowledge integration from information encoded in context versus information encoded in model weights during pretraining, evaluating a set of open models implicitly, without chain of thought. We find that accuracy decays sharply with increased composition length for both pretrained and in-context knowledge. Information presented in-context, however, substantially outperforms deduction over information encoded in weights. These results quantify a fundamental limitation of current models with direct implications for prompt-based control of agent behavior and for continual learning strategies, and they provide a foundation for developing training, prompting, and integration methods that support deeper reasoning. 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/2610.41169 — 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 2026-11-02T04:42:12.353Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).