mlsanityData to 14 Oct 2026

Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

arXiv 2604.11407 ↗First posted 13 Apr 2026cs.CL cs.AIcited by 5

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

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 textitSelf-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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 37 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

28 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers18 Jun

Other references · 27

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2021Program Synthesis with Large Language Modelscited by 3,637
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  8. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2015Teaching Machines to Read and Comprehendcited by 1,049
  11. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  12. 2023In-Context Retrieval-Augmented Language Modelscited by 702
15 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  2. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  3. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 101
  4. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89
  5. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  6. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  7. 2025BLEUBERI: BLEU is a surprisingly effective reward for instruction followingcited by 17
  8. 2025GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesiscited by 12
  9. 2025Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Frameworkcited by 8
  10. 2025Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGcited by 8
  11. 2025Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigationcited by 8
  12. 2026Adaptive Stopping for Multi-Turn LLM Reasoningcited by 7
  13. 2026SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assemblycited by 5
  14. 2026Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTScited by 5
  15. 2025RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Dissecting Failure Dynamics in Large Language Model Reasoningcited by 2
  2. 2026Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generationcited by 1
  3. 2026Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generationcited by 0
  4. 2026Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrievalcited by 0
  5. 2026No=esis: Deterministic-First Retrieval with Two-Tier Context Hydration for Factuality-Critical Queries on Small Local Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ImpRAG: Retrieval-Augmented Generation with Implicit Queries
  2. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  3. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  4. 2026Predictive Prefetching for Retrieval-Augmented Generation
  5. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  6. 2025Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding
  7. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
  8. 2026Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval