RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
[Sztuczna inteligencja] Autorzy: Yilun Hao, Krishna Sayana, Isabella Ye i 4 więcej
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 primiti…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja