Metraipolis › archive › dc_c9cc2e0c8d3d

Realize What Matters: Principled Context Representation for Large-Scale Reasoning — arXiv:2609.27173

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27173
License (as archived)
CC0-1.0
Archived
2026-10-08T10:04:47.277Z
SHA-256 of the archived text
ad73010c091a0c3926547a43f6b90d306537e69b232ce2296f0f03e2316b1c8f
Stable URL of this page
https://metraipolis.com/documento/dc_c9cc2e0c8d3d

How to cite

Realize What Matters: Principled Context Representation for Large-Scale Reasoning — arXiv:2609.27173 — arXiv (en), https://arxiv.org/abs/2609.27173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9cc2e0c8d3d (Metraipolis archive dc_c9cc2e0c8d3d, sha256 ad73010c091a0c3926547a43f6b90d306537e69b232ce2296f0f03e2316b1c8f)
BibTeX
@misc{dcc9cc2e0c8d3d,
  title = {Realize What Matters: Principled Context Representation for Large-Scale Reasoning — arXiv:2609.27173},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27173},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9cc2e0c8d3d; sha256 ad73010c091a0c3926547a43f6b90d306537e69b232ce2296f0f03e2316b1c8f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast, heterogeneous sources far beyond model context limits. Existing approaches tackle this challenge by organizing information into more manageable representations over which models can reason, such as graphs, textual memories, and retrieval collections. These representations dictate what downstream reasoning is possible and, ultimately, whether it succeeds; yet their design and construction remain largely ad hoc. In this work, drawing on the cognitive theory of relevance realization, we propose concrete principles for designing AI systems that construct effective representations of very large contexts. We analyze existing approaches and show how their successes and failures map onto their alignment with these principles, and introduce R3Con, a harness designed to operationalize the principles more systematically. We evaluate R3Con against nine state-of-the-art baselines on two recent benchmarks of reasoning over large document corpora. On these benchmarks, R3Con substantially outperforms the strongest baseline, by $20$ and $8.4$ percentage points. It also enables smaller models to outperform much larger ones: R3Con with 4B and 9B models outperforms all evaluated 35B baselines, while R3Con with a 35B-A3B model outperforms Claude Code with Claude-Sonnet-5 at $3.7\times$ lower cost. Our results show that context representations following our principled approach can reduce reliance on model scale, pointing toward a future of AI systems with frontier-level performance powered by smaller models. Our code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.27173 — 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 2026-10-08T09:11:49.595Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).