Paper Citation Record · LEDGER

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models

As of 8 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.28979.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.28979 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T16:13:28.172044Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 47d632a7-75a0-46e7-b2cc-b9ca302a5004 · outbound

This paper cites Prompt caching (openai api guide), 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Prompt caching (openai api guide), 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.358716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66b2ae3e-05a1-4993-932c-2a775301f8d0 · outbound

This paper cites Prompt caching with the claude api (cookbook), 2024.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Prompt caching with the claude api (cookbook), 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.457366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a93af632-4c6b-4e8d-9bb5-814b1e75bb78 · outbound

This paper cites Don’t do rag: When cache-augmented generation is all you need for knowledge tasks.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Don’t do rag: When cache-augmented generation is all you need for knowledge tasks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.597380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ec2755-9db9-4920-af8c-4c1fc2aeafcc · outbound

This paper cites TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.720305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61af9915-7d3a-4b02-8761-81b3971da359 · outbound

This paper cites Tenenbaum, and Igor Mordatch.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Tenenbaum, and Igor Mordatch

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.820512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ba78acf-6b70-4c4a-a823-5264b14ac66e · outbound

This paper cites Camel: Communicative agents for “mind” exploration of large language model society.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Camel: Communicative agents for “mind” exploration of large language model society

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:23.964227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe313ed-44e3-4f81-86b5-a055c84e1e5e · outbound

This paper cites White, Doug Burger, and Chi Wang.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models White, Doug Burger, and Chi Wang

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.111696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bf469fa-456f-4fac-9840-b5e047cc790c · outbound

This paper cites Fast state restoration in llm serving with hcache.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Fast state restoration in llm serving with hcache

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.272890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4b4657e-2984-46bd-8acc-dd1cfd846a83 · outbound

This paper cites Cache-to-cache: Direct semantic communication between large language models.arXiv preprint arXiv:2510.03215, 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Cache-to-cache: Direct semantic communication between large language models.arXiv preprint arXiv:2510.03215, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.419950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159f3e37-0d93-450b-b418-b552903a7084 · outbound

This paper cites Kvcomm: Enabling efficient llm communication through selective kv sharing.arXiv preprint arXiv:2510.03346, 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Kvcomm: Enabling efficient llm communication through selective kv sharing.arXiv preprint arXiv:2510.03346, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.559521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1516947-d6c2-4a84-864e-f945acf52d34 · outbound

This paper cites Enabling Agents to Communicate Entirely in Latent Space.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Enabling Agents to Communicate Entirely in Latent Space

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.675190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5a6fbd-c6bb-4ed9-bc9c-bad1cd52933e · outbound

This paper cites Latent space communication via kv cache alignment.arXiv preprint arXiv:2601.06123, 2026.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Latent space communication via kv cache alignment.arXiv preprint arXiv:2601.06123, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.824359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49b2ef81-e460-4c67-8259-d8bf0f037826 · outbound

This paper cites Spurious Forgetting in Continual Learning of Language Models.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Spurious Forgetting in Continual Learning of Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:24.960751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd989b5c-65d5-44a8-bd5a-5ef09f145d17 · outbound

This paper cites Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.096541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d981711d-a260-4a57-af49-b132083269c1 · outbound

This paper cites On the Convergence of Gradient Descent on Learning Transformers with Residual Connections.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models On the Convergence of Gradient Descent on Learning Transformers with Residual Connections

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.234835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0d0b4c9-d09b-455a-8567-2d32b262f6bb · outbound

This paper cites Information-theoretical analysis of a transformer-based generative ai model.Entropy, 27(6):589, 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Information-theoretical analysis of a transformer-based generative ai model.Entropy, 27(6):589, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.386658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d081d0-88e8-405f-9ff2-54f34e112eb6 · outbound

This paper cites Kqml as an agent commu- nication language.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Kqml as an agent commu- nication language

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.517380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0be6457c-aa11-4905-a85e-f7bd085c2e7e · outbound

This paper cites Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera y Arcas.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera y Arcas

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.590802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ff3b5c-537e-4ed7-bea4-7fb6f371ddcb · outbound

This paper cites Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.660212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c1cac6-a2e7-4b31-85f6-80957a797208 · outbound

This paper cites Fedmd: Heterogenous federated learning via model distillation.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Fedmd: Heterogenous federated learning via model distillation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.729023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be67c15-8d3c-4bcb-bd77-e79ab91fdfac · outbound

This paper cites Foerster, Yannis M.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Foerster, Yannis M

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.779872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e63681a-65df-4389-8b45-307d7d4066f8 · outbound

This paper cites Emergent Multi-Agent Communication in the Deep Learning Era.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Emergent Multi-Agent Communication in the Deep Learning Era

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.880074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf31252-afc1-4090-a895-c386dd8af19c · outbound

This paper cites Metagpt: Meta programming for a multi-agent collaborative framework.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Metagpt: Meta programming for a multi-agent collaborative framework

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:25.976644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f8928f-bedb-457e-9619-998cc8141d5c · outbound

This paper cites Mixture-of-agents enhances large language model capabilities.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Mixture-of-agents enhances large language model capabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.043401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f1a4a25-3fe1-4950-833c-81a8a7ff63b0 · outbound

This paper cites Gonzalez, M.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Gonzalez, M

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.155502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9909936-1071-4765-a82b-2d6ae1481f69 · outbound

This paper cites Learning to decode collaboratively with multiple language models.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Learning to decode collaboratively with multiple language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.234112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77bfa0dc-7d84-43ed-ad37-ba465509e669 · outbound

This paper cites Plummer, Zhaoran Wang, and Hongxia Yang.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Plummer, Zhaoran Wang, and Hongxia Yang

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.308750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef4d6cd-602e-4e50-b07c-9dcbe945ac61 · outbound

This paper cites Communicating activations between language model agents.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Communicating activations between language model agents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.404015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c480dc-9045-4558-8dc9-abe43a6d3ca9 · outbound

This paper cites Augmenting multi-agent communication with state delta trajectory.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Augmenting multi-agent communication with state delta trajectory

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.477573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e1072f-af9d-4094-85ca-11014d0fa7c9 · outbound

This paper cites HeteroTune: Efficient federated learning for large heterogeneous models, 2024.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models HeteroTune: Efficient federated learning for large heterogeneous models, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.587610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1deb6e-06d6-4d9a-9e7b-ff81144ebc36 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.699897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc31537-b8c5-43f5-a8d3-63ef65e5e488 · outbound

This paper cites Chunkattention: Efficient self-attention with prefix- aware KV cache and two-phase partition, 2024.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Chunkattention: Efficient self-attention with prefix- aware KV cache and two-phase partition, 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.845299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0910cb-50a0-427f-9a09-94e4044498dd · outbound

This paper cites Prompt cache: Modular attention reuse for low-latency inference.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Prompt cache: Modular attention reuse for low-latency inference

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:26.946614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029b43f5-0307-47bf-8cb4-6127c03d9dfe · outbound

This paper cites KVFlow: Efficient prefix caching for accelerating LLM-based multi-agent workflows, 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models KVFlow: Efficient prefix caching for accelerating LLM-based multi-agent workflows, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.082954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b82bf2-c38e-4b41-966d-744813a4306c · outbound

This paper cites IMPRESS: An importance-informed multi-tier prefix KV storage system for LLM serving.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models IMPRESS: An importance-informed multi-tier prefix KV storage system for LLM serving

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.224800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb50b2e-b123-4d9e-96d1-9ab608d22437 · outbound

This paper cites SemshareKV: Efficient KVcache sharing for semantically similar prompts via token-level LSH matching.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models SemshareKV: Efficient KVcache sharing for semantically similar prompts via token-level LSH matching

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.343368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a54c289-cd46-490c-a4cf-4dcb5662e0e6 · outbound

This paper cites KVShare: An LLM service system with efficient and effective multi-tenant KV cache reuse, 2025.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models KVShare: An LLM service system with efficient and effective multi-tenant KV cache reuse, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.509715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f17a95b-9257-4654-9e44-d69c08a02ce8 · outbound

This paper cites Towards a collaborative memory for agentic workflow: Breaking the prefix barrier with segment-level KV cache sharing.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Towards a collaborative memory for agentic workflow: Breaking the prefix barrier with segment-level KV cache sharing

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.633985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96504737-59a9-4d4b-9767-b8391711ffa5 · outbound

This paper cites Yang, Tony Q.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Yang, Tony Q

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.773417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4322cb9-1687-43ac-9a3a-29742df65771 · outbound

This paper cites Droidspeak: KV cache sharing for cross-LLM communication and multi-LLM serving, 2024.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Droidspeak: KV cache sharing for cross-LLM communication and multi-LLM serving, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.917557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 153a458e-2b8a-42ab-bef6-f438a146b53e · outbound

This paper cites LRAgent: Efficient KV cache sharing for multi-LoRA LLM agents, 2026.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models LRAgent: Efficient KV cache sharing for multi-LoRA LLM agents, 2026

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:27.958668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa78b9e9-5874-4483-81e6-e9ab174ddf2f · outbound

This paper cites The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:28.038637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 908835d7-7904-44d6-8076-396e1e2427a6 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T16:13:28.096757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5e5a77-5eca-4b6e-b9f5-38571831464b · outbound

This paper cites Venite Ad Me Omnes.

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models Venite Ad Me Omnes

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-08-03T16:13:28.172044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.