LACO introduces Iterative Latent Deliberation, Cross-Horizon Saliency Attribution, and Structured Semantic Knowledge Distillation to enable low-latency latent communication in collaborative driving while preserving performance in CARLA simulations.
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM- based Multi-agent Systems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
QKVShare enables efficient quantized KV-cache handoff for on-device multi-agent LLMs, cutting TTFT versus re-prefill across tested contexts while adaptive quantization stays competitive with uniform baselines on GSM8K.
A single shared asymmetrically compressed KV cache pool enables up to 15 concurrent LLM agents with 2.91x compression, 97.7% memory reduction, and only +0.57% perplexity increase on Llama-3-8B.
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
citing papers explorer
-
LACO: Adaptive Latent Communication for Collaborative Driving
LACO introduces Iterative Latent Deliberation, Cross-Horizon Saliency Attribution, and Structured Semantic Knowledge Distillation to enable low-latency latent communication in collaborative driving while preserving performance in CARLA simulations.
-
QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs
QKVShare enables efficient quantized KV-cache handoff for on-device multi-agent LLMs, cutting TTFT versus re-prefill across tested contexts while adaptive quantization stays competitive with uniform baselines on GSM8K.
-
PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
A single shared asymmetrically compressed KV cache pool enables up to 15 concurrent LLM agents with 2.91x compression, 97.7% memory reduction, and only +0.57% perplexity increase on Llama-3-8B.
-
TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
-
Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.