Paper Citation Record · LEDGER

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference

As of 9 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2608.03741.

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

pith.paper-citation-record.v1
2608.03741 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:48:37.632916Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

33 of 33 outbound references displayed

verified exact1
verified fuzzy20
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5b1323bf-6dc8-4b82-8327-b798dc56b6a0 · outbound

This paper cites Inside NVIDIA Groq 3 LPX: The Low- Latency Inference Accelerator for the NVIDIA Vera Rubin Platform,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Inside NVIDIA Groq 3 LPX: The Low- Latency Inference Accelerator for the NVIDIA Vera Rubin Platform,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:42.015889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4917b56c-8c02-4fbf-aceb-270e8b77fd89 · outbound

This paper cites Web agents with world models: Learning and leveraging environment dynamics in web navigation,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Web agents with world models: Learning and leveraging environment dynamics in web navigation,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.841775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4bc64967-f6e2-4e7b-9463-98dfd1d95a08 · outbound

This paper cites Llmservingsim 2.0: A unified simulator for heterogeneous and disaggregated llm serving infrastructure,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Llmservingsim 2.0: A unified simulator for heterogeneous and disaggregated llm serving infrastructure,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.709830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e94c5b14-61c8-495c-b5ae-0e421252978b · outbound

This paper cites DeepSeek-V3 Technical Report.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference DeepSeek-V3 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:34.861373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e24d336-76dc-4180-af7c-f5f96195ddcb · outbound

This paper cites Deepseek-v4 technical report,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Deepseek-v4 technical report,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.594627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4a8b2a17-e09e-4ba0-935c-11cbfd20c0b9 · outbound

This paper cites Coral npu: A full-stack platform for edge ai,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Coral npu: A full-stack platform for edge ai,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.414349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8e296dde-dde5-46b4-948d-f2c40e5f3a5f · outbound

This paper cites The llama 3 herd of models,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference The llama 3 herd of models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.208892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 039c93ab-396d-410f-9505-dad9ac140e02 · outbound

This paper cites Webvoyager: Building an end-to-end web agent with large multimodal models,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Webvoyager: Building an end-to-end web agent with large multimodal models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:41.052218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 72d5d76a-1401-4d01-b148-785036f11671 · outbound

This paper cites Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:35.375376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ef4ac6-1b75-4ca8-8f78-0a64a8dca847 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively mul- timodal ai innovation,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference The llama 4 herd: The beginning of a new era of natively mul- timodal ai innovation,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:40.843456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 45a99a89-d9d7-410d-a84a-0c2143f6064b · outbound

This paper cites KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:35.603804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f9b2ba-9676-4e35-8bee-371649d18d97 · outbound

This paper cites NVLink and NVLink switch,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference NVLink and NVLink switch,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:40.625721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cfd5190e-6086-4fda-ac4a-a9ae272a20e7 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference gpt-oss-120b & gpt-oss-20b Model Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:35.787007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f32fe468-4421-4c07-8a26-922c78e6c6a7 · outbound

This paper cites Splitwise: Efficient generative LLM inference using phase splitting.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Splitwise: Efficient generative LLM inference using phase splitting

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:35.895560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc07b3d-4afd-49c6-8169-881cabb7c74f · outbound

This paper cites The berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference The berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:40.441203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a4f6c8e8-3abf-4dce-9528-1ad848211172 · outbound

This paper cites Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:40.200944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4a368799-2552-4418-82cb-4f0159ef359d · outbound

This paper cites Qwen3 Technical Report.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Qwen3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:36.285131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f3e952b-eed5-4671-94d6-7026ca733b78 · outbound

This paper cites Microscopiq: Acceler- ating foundational models through outlier-aware microscaling quantiza- 12 tion,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Microscopiq: Acceler- ating foundational models through outlier-aware microscaling quantiza- 12 tion,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.974689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94a5c529-7c54-4469-ac12-baa9df6dbcda · outbound

This paper cites Longcodebench: Evaluating coding LLMs at 1m context windows,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Longcodebench: Evaluating coding LLMs at 1m context windows,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.785628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4833d5a2-b500-44c4-a4c2-19fff570c7ee · outbound

This paper cites Microscaling Data Formats for Deep Learning.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Microscaling Data Formats for Deep Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:36.545613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d7092fc-aef3-42df-b48d-c8be21df4baa · outbound

This paper cites Step-3 is large yet affordable: Model-system co-design for cost-effective decoding,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Step-3 is large yet affordable: Model-system co-design for cost-effective decoding,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:36.629024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fdd8148-cabc-4dca-ba8c-bd36b470d259 · outbound

This paper cites Attention is all you need,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Attention is all you need,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.608902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 825ce3a6-33d0-4c3d-abf2-746d907971ec · outbound

This paper cites MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:48:38.002161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 35cc6f7d-513c-4d5d-af3b-4658d545bf61 · outbound

This paper cites Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:36.864717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 470641ae-f7fd-491a-a5df-906aa9c61427 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.434810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 42076615-39d6-4aac-b043-0079714b0cd1 · outbound

This paper cites FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:37.037252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2eee7e2-fdca-4fa4-97a4-7e46e8059e95 · outbound

This paper cites MR-GSM8K: A meta- reasoning benchmark for large language model evaluation,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference MR-GSM8K: A meta- reasoning benchmark for large language model evaluation,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.257272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0bdc0f63-0938-462b-b470-c30d5c262fbf · outbound

This paper cites Mase: An efficient represen- tation for software-defined ml hardware system exploration.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Mase: An efficient represen- tation for software-defined ml hardware system exploration

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:39.102770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7cb9be3a-f18e-4d21-9ba3-f2f09ae1db76 · outbound

This paper cites Llmcompass: Enabling efficient hardware design for large language model inference,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Llmcompass: Enabling efficient hardware design for large language model inference,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:37.345909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e468c8-ab4a-4e0c-8ff8-116626317461 · outbound

This paper cites Glm-4.6,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Glm-4.6,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:38.921208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0024333a-9f93-4412-914d-fe1da8eb7ba8 · outbound

This paper cites Distserve: disaggregating prefill and decoding for goodput-optimized large language model serving,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Distserve: disaggregating prefill and decoding for goodput-optimized large language model serving,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:38.671433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 008bf376-6b11-4ac8-af99-73d24bd3d643 · outbound

This paper cites Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving,.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:48:38.421954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1bec9d0f-f8b6-4ec7-8115-65790dc4223e · outbound

This paper cites The Llama 3 Herd of Models.

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:35.172321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.