paper-with-me

홈 › Papers

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

2025-12-27 · Bharath Nunepalli 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.

📄 PDF Abstract BibTeX arXiv:2601.00841

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

2026-09-15 · Aurélien Pellet, Julien Perez, Marie Puren arxiv

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where…

Query Routing for Retrieval-Augmented Language Models

2025-05-29 · Jiarui Zhang, Xiangyu Liu, Yong Hu, Chaoyue Niu 외

Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent r…

Contrastive LearningRAGRetrievalRetrieval-augmented Generation

Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation

2026-05-07 · Abhijit Talluri, Pujith Anne, Bhagavan Choudary Pendiyala, Raghavendra Chilukuri arxiv

Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the structural complexity of the code under modification, yet existing systems select topologi…

Code Generation

Unsupervised Query Routing for Retrieval Augmented Generation

2025-01-14 · Feiteng Mu, Liwen Zhang, Yong Jiang, Wenjie Li 외

Query routing for retrieval-augmented generation aims to assign an input query to the most suitable search engine. Existing works rely heavily on supervised datasets that require extensive manual annotation, resulting in…

RetrievalRetrieval-augmented Generation

EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA

2026-04-24 · Jaspreet Singh Nahal arxiv

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We intro…