mlsanityData to 7 Oct 2026

When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration

arXiv 2604.13349 ↗First posted 14 Apr 2026cs.LGcited by 5

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Multi-agent LLM systems are moving beyond discrete-token messages toward richer relays that preserve internal state. Recent work such as LatentMAS transmits full key-value (KV) caches between agents but pays a high memory and communication cost. We adapt KV-cache eviction to this setting and introduce Orthogonal BackFill (OBF), which injects a low-rank residual from the discarded KV states back into the retained ones, orthogonal to what is already kept. With only 9.9%-20.2% of the prompt KV retained, compressed relay cuts bandwidth by 4.7× and GPU memory by 8% at under 5% wall-clock overhead, and stays close to full relay in accuracy across nine benchmarks, ahead of it on several. OBF matches or improves over headwise eviction on all nine, and its gain is proportional to the accuracy gap eviction opens against full relay (r=0.78 across three model scales), so it gives back part of what eviction takes. Code is available at https://github.com/markli404/When-Less-Latent-Leads-to-Better-Relay.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 19 of its 29 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

19 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Augmenting Multi-Agent Communication with State Delta Trajectory24 Jun
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 17

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  3. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  4. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  8. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  10. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  11. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationcited by 571
  12. 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Timecited by 428
5 more
  1. 2024RazorAttention: Efficient KV Cache Compression Through Retrieval Headscited by 99
  2. 2024Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoningcited by 96
  3. 2024DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMscited by 42
  4. 2023Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learningcited by 9
  5. 2026Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inferencecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLMcited by 5
  2. 2026When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMscited by 3
  3. 2026Semantic Register Compression in Multi-Agent LLM Cascadescited by 0
  4. 2026Receiver-Conditioned Latent Communication gives 94% CacheBackcited by 0
  5. 2026Draft-KV: Learning Useful Latent Communication Between Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration
  2. 2026RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
  3. 2026Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays
  4. 2026Latent Cache Flow: Model-to-Model Communication Without Text
  5. 2026PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
  6. 2026TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
  7. 2026LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
  8. 2026Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?