Year: 2026
Type: conference-paper
Abstract: We revisit retrieval-augmented generation (RAG) by embedding retrieval control directly into generation.Instead of treating retrieval as an external intervention, we express retrieval decisions within token-level decoding, enabling end-to-end coordination without additional controllers or classifiers.Under the paradigm of Retrieval as Generation, we propose GRIP (Generation-guided Retrieval with Information Planning), a unified framework in which the model regulates retrieval behavior through control-token emission.Central to GRIP is Self-Triggered Information Planning, which allows the model to decide when to retrieve, how to reformulate queries, and when to terminate, all within a single autoregressive trajectory.This design tightly couples retrieval and reasoning and supports dynamic multi-step inference with on-the-fly evidence integration.To supervise these behaviors, we construct a structured training set covering answerable, partially answerable, and multi-hop queries, each aligned with specific token patterns.Experiments on five QA benchmarks show that GRIP surpasses strong RAG baselines and is competitive with GPT-4o while using substantially fewer parameters.
Authors: Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, Wei Ye
Institutions: Peking University, Hebei University of Technology, Hugging Face
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166834131