Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs

arXiv:2609.17564 · cs.LG, cs.IR · Submitted 2026-07-23 · Read on arXiv

cs.LG, cs.IR

Submitted: 2026-07-23

Updated: 2026-07-23

Comments: This Paper is accepted and presented at ICML Scale Workshop 2026. https://scale-icml-2026.github.io/accepted_papers.html (Paper ID :72)

Project page: https://scale-icml-2026.github.io/accepted_papers.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks