Receiver-Conditioned Latent Communication gives 94% CacheBack

arXiv:2609.32046 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/maxr0ssi/rclc

Terminology

• Accuracy — 52× in this paper · explained in 1 episode
• KV cache — 15× in this paper · explained in 3 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Multi-Agent System — 5× in this paper · explained in 6 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Hybrid Architectures — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Thinking mode — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Hybrid Models — 1× in this paper · explained in 2 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
• Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
• NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
• Latent Cache Flow: Model-to-Model Communication Without Text
• Qwen3 Technical Report
• Latent Collaboration in Multi-Agent Systems

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection