PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction
cs.LG
Submitted: 2026-09-28
Updated: 2026-10-06
Terminology
Sources
- Small Language Models are the Future of Agentic AI
- TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
- Reinforcement Learning for Long-Horizon Interactive LLM Agents
- Latent Space Communication via K-V Cache Alignment
- MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
- The Llama 3 Herd of Models
- Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
- Characterizing How Complex Agentic AI Systems Handle General Tasks: A Trace-Based Simulation Study
- BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
- Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Adaptive Minds: Empowering Agents with LoRA-as-Tools
- Model Fusion with Multi-LoRA Inference for Tool-Enhanced Game Dialogue Agents
- PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
- Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks