Metraipolis › archive › dc_cae38d92bea7

RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing — arXiv:2610.10507

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10507
License (as archived)
CC0-1.0
Archived
2026-10-08T11:09:57.507Z
SHA-256 of the archived text
43240c39545a5e9ab39805335f227f32fdfcd669fc5bbcc5d489383cc7b59a24
Stable URL of this page
https://metraipolis.com/documento/dc_cae38d92bea7

How to cite

RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing — arXiv:2610.10507 — arXiv (en), https://arxiv.org/abs/2610.10507 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cae38d92bea7 (Metraipolis archive dc_cae38d92bea7, sha256 43240c39545a5e9ab39805335f227f32fdfcd669fc5bbcc5d489383cc7b59a24)
BibTeX
@misc{dccae38d92bea7,
  title = {RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing — arXiv:2610.10507},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10507},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cae38d92bea7; sha256 43240c39545a5e9ab39805335f227f32fdfcd669fc5bbcc5d489383cc7b59a24},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10507. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but remain largely retrieval-centric. However, in many tasks, the evidence required for a solution is not explicitly present in any single source item. Instead, it must be derived through filtering, aggregation, or computation across multiple source items. In this work, we introduce RECAST (Routing Evidence through Computation, Access, and Synthesized Tools), a learned framework that formulates evidence construction as a sequential decision process over heterogeneous retrieval and computation operations, allowing evidence to be actively derived rather than merely retrieved. A lightweight RouterLM iteratively selects and formulates primitive operations or specifies customized operations for a frozen CompilerLM to translate into executable code. Once it judges the evidence sufficient, RouterLM passes the accepted evidence to a frozen AnswerLM to produce the final solution. We train RouterLM with supervised fine-tuning (SFT) followed by group relative policy optimization (GRPO). Across six heterogeneous benchmark families, RECAST achieves a mean success rate of 75.6%, outperforming the strongest large-model baseline by 15.9%. Moreover, training enables the Qwen3.5-9B RouterLM to outperform a training-free Gemini 3.5 Flash RouterLM by 5.0%. On three held-out benchmarks, RECAST improves over the strongest baseline by 15.0% on average, demonstrating strong zero-shot generalization across tasks and heterogeneous source representations.

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/2610.10507 — 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 2026-10-08T10:14:05.994Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).