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

• URL: http://arxiv.org/abs/2601.00841v1
• Date: Sat, 27 Dec 2025 15:37:53 GMT
• Title: SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes
• Abstract summary: This work models per- query control as a small discrete action: choose a retrieval depth and a generation mode (guarded vs. auto) or refuse.<n>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.<n>Two simple policy-learning objectives are evaluated: supervised classification of the per-state best action and a reward-weighted variant.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Unleashing the Potential of Large Language Models: A Blueprint for Real-Time, Enterprise-Ready Deployments [11.71713024399078]
  We present a unified, pattern-driven LLMOps architecture integrating real-time data ingestion, continual learning, retrieval-augmented generation, and human-in-the-loop feedback.<n>The result reduces latency-cost-accuracy trade-offs while supporting auditability and rollback for high-risk sectors such as health care and finance.
  arXiv  Detail & Related papers  (2026-08-01T03:40:22Z)
• FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning [63.80677039120727]
  FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model.<n>To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation.<n>The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals.
  arXiv  Detail & Related papers  (2026-06-23T07:21:36Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization [20.910779784518798]
  Group Relative Policy Optimization (GRPO) has been emerging as a leading choice, but its reliance on sparse outcome rewards severely limits credit assignment across intermediate steps.<n>We propose a two-stage model with a frozen hidden-state probe estimating belief-consistency and a lightweight attention-based head correcting it toward grounded correctness.<n> Experimental results show that PAIR achieves the highest AUROC on contaminated trajectories while operating at negligible inference cost.
  arXiv  Detail & Related papers  (2026-05-18T05:39:30Z)
• Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR [53.27792011950384]
  Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models.<n>We propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR.<n>Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts.
  arXiv  Detail & Related papers  (2026-05-15T08:22:59Z)
• Optimistic Feasible Search for Closed-Loop Fair Threshold Decision-Making [0.0]
  We study online learning of a one-dimensional threshold policy from bandit feedback.<n>We propose Optimistic Feasible Search (OFS), a simple grid-based method that maintains confidence bounds for reward and constraint residuals.
  arXiv  Detail & Related papers  (2025-12-26T10:44:40Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment [44.33395106709674]
  Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback.<n>Current RLVR methods typically assign the same reward to every token.<n>This coarse-grained feedback hampers precise credit assignment, making it hard for models to identify which reasoning steps lead to success or failure.
  arXiv  Detail & Related papers  (2025-08-04T11:06:08Z)
• Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning [45.10424242207931]
  Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs)<n>We introduce a novel method ReasonRAG that automatically constructs RAG-ProGuide, a high-quality dataset providing process-level rewards for query generation, evidence extraction, and answer generation.<n>With the process-level policy optimization, the proposed framework empowers LLMs to autonomously invoke search, generate queries, extract relevant evidence, and produce final answers.
  arXiv  Detail & Related papers  (2025-05-20T08:21:00Z)
• Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models [71.34520793462069]
  Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments.<n>We introduce a novel algorithm regularizing unsupervised RL towards imitating trajectories from unlabeled behavior datasets.<n>We demonstrate the effectiveness of this new approach in a challenging humanoid control problem.
  arXiv  Detail & Related papers  (2025-04-15T10:41:11Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs [0.0]
  We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging theity of LLMs.<n>In this system, LLM checkers vote on the acceptability of a generated output, regenerating it if a threshold of disapproval is reached.
  arXiv  Detail & Related papers  (2024-07-24T04:27:55Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)
• Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning [56.26889258704261]
  We propose a novel "disentangled" decision-making method, Semantically Aligned task decomposition in MARL (SAMA) SAMA prompts pretrained language models with chain-of-thought that can suggest potential goals, provide suitable goal decomposition and subgoal allocation as well as self-reflection-based replanning. SAMA demonstrates considerable advantages in sample efficiency compared to state-of-the-art ASG methods.
  arXiv  Detail & Related papers  (2023-05-18T10:37:54Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.