paper-with-me

Papers

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

2025-04-02 · Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta, Venkataramana Runkana

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on knowledge-intensive tasks, including opendomain question answering and complex reasoning. Our framework integrates two complementary techniques: Policy-Optimized RetrievalAugmented Generation (PORAG), which optimizes the use of retrieved information, and Adaptive Token-Layer Attention Scoring (ATLAS), which dynamically determines retrieval timing and content based on contextual needs. Together, these techniques enhance both the utilization and relevance of retrieved content, improving factual accuracy and response quality. Designed as a lightweight solution compatible with any Transformer-based LLM without requiring additional training, our framework excels in knowledge-intensive tasks, boosting output accuracy in RAG settings. We further propose CRITIC, a novel method to selectively compress key-value caches by token importance, mitigating memory bottlenecks in long-context applications. The framework also incorporates test-time scaling techniques to dynamically balance reasoning depth and computational resources, alongside optimized decoding strategies for faster inference. Experiments on benchmark datasets show that our framework reduces hallucinations, strengthens domain-specific reasoning, and achieves significant efficiency and scalability gains over traditional RAG systems. This integrated approach advances the development of robust, efficient, and scalable RAG systems across diverse applications.

📄 PDF Abstract BibTeX arXiv:2504.01281

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
WordPiece 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Active Inference as the Test-Time Scaling Law for Physical AI Agents

2026-06-22 · Omar Hashash, Christo Kurisummoottil Thomas, Walid Saad, Merouane Debbah 외 arxiv

In this paper, a novel test-time scaling law for physical artificial intelligence (AI) agents is introduced. This scaling law enables physical AI agents to reason with their world models to generalize in unforeseen scena…

Reinforcement LearningBayesian InferenceAutonomous Driving

Compute Aligned Training: Optimizing for Test Time Inference

2026-04-27 · Adam Ousherovitch, Ambuj Tewari arxiv

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL),…

Reinforcement Learning

Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures

2026-05-09 · Linhai Zhang, Yulan He arxiv

Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process. In this work, we study Test-Time Personalization (TTP) along an un…

Text Generation

Provable and Practical In-Context Policy Optimization for Self-Improvement

2026-03-02 · Tianrun Yu, Yuxiao Yang, Zhaoyang Wang, Kaixiang Zhao 외 arxiv

We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agent optimizes its response in context usin…

Mathematical Reasoning

Scaling Offline RL via Efficient and Expressive Shortcut Models

2025-05-28 · Nicolas Espinosa-Dice, Yiyi Zhang, Yiding Chen, Bradley Guo 외

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due …

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)