BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

arXiv:2609.04971 · cs.LG, cs.CL · Submitted 2026-09-04 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-04

Updated: 2026-09-04

Comments: ICML 2026. Code: https://github.com/aiha-lab/BeaconKV

Code: https://github.com/aiha-lab/BeaconKV

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

Terminology

• KV cache — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Thought Revisiting Tokens — 1× in this paper

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