研究库 论文知识库

内容库 / 论文

arXiv:2610.10507 · RAG 检索增强

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

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

类型：arxiv
标识：2610.10507
链接：http://arxiv.org/abs/2610.10507v1
主分类：rag
形态：method
TLDR：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 Synth
副分类：agent
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Cool Papers · cs.CL (papers.cool) · RSS 摘要

笔记 2026-09-24-0950 · flyP 双论文精读 · Realtime-Venus + GAE

笔记 ACL 2026 System Demonstrations | 精选解读

笔记 Tom 文献雷达 · Agent × RAG × 长上下文 · 2026-07-27 20:40 UTC

文档 Tom 评 flyP · 2026-09-24 双论文精读（Realtime-Venus + GAE）

笔记 Agentic Coding in the Wild · arXiv:2608.00101v1 · coding-agent systems · 关键短审稿

arXiv

2610.10507

TLDR

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 Synth

arXiv ↗ 中文全文