mlsanityData to 7 Oct 2026

SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes

arXiv 2601.00841 ↗First posted 27 Dec 2025cs.LGcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented generation (RAG) introduces a practical control problem: retrieval depth and generation behavior must be chosen per query to satisfy service-level objectives (SLOs) such as cost, refusal rate, and hallucination risk. This work models per-query control as a small discrete action: choose a retrieval depth and a generation mode (guarded vs. auto), or refuse. An offline logged dataset is constructed from SQuAD 2.0 by executing each action and recording accuracy, token cost, hallucination/refusal indicators, and an SLO-weighted reward. Two simple policy-learning objectives are evaluated: supervised classification of the per-state best action (Argmax-CE) and a reward-weighted variant (Argmax-CE-WT). Across the evaluated settings, a strong fixed baseline (low k, guarded prompting) performs competitively; learned policies mainly provide additional cost savings under a quality-focused SLO and can exhibit refusal collapse under a cheap SLO when refusal is heavily rewarded. The contribution is a reproducible case study of SLO-aware control for RAG pipelines, emphasizing failure modes and reporting conventions rather than proposing a new retriever or language model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 17 references that are in the map. First posted on arXiv 27 Dec 2025.

Builds on

10 of 17 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  8. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  9. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
  2. 2025RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning
  3. 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation
  4. 2026When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1
  5. 2026Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?
  6. 2026The RAT: A Unified Bayesian Model for RAG Evaluation
  7. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
  8. 2024A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems