Paper Citation Record · LEDGER

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.12123.

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

pith.paper-citation-record.v1
2608.12123 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:20:45.919107Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

37 of 37 outbound references displayed

verified exact8
verified fuzzy19
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e5f7ef1-a297-406b-8160-f9c43968773e · outbound

This paper cites Infercept: Efficient inter- cept support for augmented large language model inference.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Infercept: Efficient inter- cept support for augmented large language model inference

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.751159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ce60ec30-1618-4116-85a1-6db51b7d118a · outbound

This paper cites Achieving anonymity via cluster- ing.ACM Transactions on Algorithms, 6(3):1–19,.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Achieving anonymity via cluster- ing.ACM Transactions on Algorithms, 6(3):1–19,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.740157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed5a85b3-54ee-4597-88b4-4b17b0787213 · outbound

This paper cites On r- gatherings on the line.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control On r- gatherings on the line

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.791418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b18933-04b7-43b4-8895-bdc6f530b5b5 · outbound

This paper cites Throughput maximization of real-time scheduling with batching.ACM Transactions on Algorithms, 5 (2):18:1–18:17, 2009.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Throughput maximization of real-time scheduling with batching.ACM Transactions on Algorithms, 5 (2):18:1–18:17, 2009

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.795926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cec4a3c-f407-411f-a229-62003db99f0a · outbound

This paper cites InProceedings of the 43rd International Conference on Machine Learning, volume 306 ofProceedings of Machine Learning Research.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control InProceedings of the 43rd International Conference on Machine Learning, volume 306 ofProceedings of Machine Learning Research

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.729131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a7ade955-e687-4afe-8374-99559d4cc3dd · outbound

This paper cites Joint batching and scheduling for high-throughput mul- tiuser edge AI with asynchronous task arrivals.IEEE Transactions on Wireless Communications, 23(10): 13782–13795, 2024.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Joint batching and scheduling for high-throughput mul- tiuser edge AI with asynchronous task arrivals.IEEE Transactions on Wireless Communications, 23(10): 13782–13795, 2024

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.804436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb7682d9-a432-4a2e-81c5-601f924fb32a · outbound

This paper cites Murakkab: Resource-efficient agen- tic workflow orchestration in cloud platforms.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Murakkab: Resource-efficient agen- tic workflow orchestration in cloud platforms

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.717732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b9583117-5d7b-427f-b638-a4781042cbb9 · outbound

This paper cites MPK: A compiler and runtime for Mega-Kernelizing tensor programs.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control MPK: A compiler and runtime for Mega-Kernelizing tensor programs

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.706705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a500b53e-fae5-4cdd-9eb1-cee663c6408b · outbound

This paper cites Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:20:46.315555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9421b1c0-044a-47e1-90f1-126806ab7d00 · outbound

This paper cites Multi-benchmark LLM agent traces.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Multi-benchmark LLM agent traces

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.696024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eb074619-c13e-41de-bea3-d5dcf2fcee7f · outbound

This paper cites SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.824287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fed500-98c4-4cc5-bf86-96242aaad933 · outbound

This paper cites Huertas and Pascal Van Hentenryck.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Huertas and Pascal Van Hentenryck

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.828086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 297cf1b1-b459-45b3-aa8a-8478432926cb · outbound

This paper cites Asimplealgorithmfor r-gatherings on the line.Journal of Graph Algorithms and Applica- tions, 23(5):837–845, 2019.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Asimplealgorithmfor r-gatherings on the line.Journal of Graph Algorithms and Applica- tions, 23(5):837–845, 2019

Reference 13

Resolution: verified exact; doi, observed 2026-08-16T00:20:45.987246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2e6d9c3-556f-4a88-99cc-a61adea5a432 · outbound

This paper cites Mowry, Zhihao Jia, and Tianqi Chen.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Mowry, Zhihao Jia, and Tianqi Chen

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.684969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c8b80e5-71ea-4d99-b95f-61d97326dbe8 · outbound

This paper cites ThunderAgent: A simple, fast and program-aware agentic inference system, 2026.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control ThunderAgent: A simple, fast and program-aware agentic inference system, 2026

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.673301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3a983015-dbb9-4efa-9849-83ae8b58fa94 · outbound

This paper cites Laszlo and Sumitra Mukherjee.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Laszlo and Sumitra Mukherjee

Reference 16

Resolution: verified exact; doi, observed 2026-08-16T00:20:45.973341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 69abbb09-162f-41eb-b159-99b65f937c80 · outbound

This paper cites Parrot: Efficient serving of LLM-based applications with semantic variable.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Parrot: Efficient serving of LLM-based applications with semantic variable

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.659894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 780f5511-1a20-4436-9af7-a3616ace2b08 · outbound

This paper cites Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:20:46.214952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 19bd23be-4ef6-46f2-af3b-c7d05de9a95a · outbound

This paper cites Gonzalez, and Ion Stoica.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Gonzalez, and Ion Stoica

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.637527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5fface58-f691-4131-92fa-aba4ac305c78 · outbound

This paper cites NVIDIA Corporation,.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control NVIDIA Corporation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.626412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76235de1-36ce-4ac6-bb69-698a7bd19643 · outbound

This paper cites FLAME GPU 2: A framework for flexible and per- formant agent based simulation on GPUs.Software: Practice and Experience, 53(8):1659–1680, 2023.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control FLAME GPU 2: A framework for flexible and per- formant agent based simulation on GPUs.Software: Practice and Experience, 53(8):1659–1680, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.868678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40311ea0-7de5-4ccc-9c2c-72804982e4ea · outbound

This paper cites Sohel Rahman.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Sohel Rahman

Reference 22

Resolution: verified exact; doi, observed 2026-08-16T00:20:45.952723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b30d7811-fc65-4321-99a1-aeb34b0fdcf9 · outbound

This paper cites OpRAG: A Resource-Deterministic Runtime for GPU-Backed Multi-Stage RAG Workflows.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control OpRAG: A Resource-Deterministic Runtime for GPU-Backed Multi-Stage RAG Workflows

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:20:46.199189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cac9daf2-7ab1-4f5a-b336-e424aa68c12f · outbound

This paper cites MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:20:46.181049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6cb111a7-1664-441d-b9e4-e1653d15426d · outbound

This paper cites SMDP-based dynamic batching for efficient inference on GPU-based platforms.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control SMDP-based dynamic batching for efficient inference on GPU-based platforms

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.884514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8204806-6671-449a-b8d7-62ae94595694 · outbound

This paper cites Architectural implications of agentic AI workflows, 2026.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Architectural implications of agentic AI workflows, 2026

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.602961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9fa2fd2f-c12b-4fc5-abfa-3b4390e9c931 · outbound

This paper cites GPUOS: A GPU operating system primitive for transparent operation fusion, 2026.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control GPUOS: A GPU operating system primitive for transparent operation fusion, 2026

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.590840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3aaeee35-bbac-42a3-9ac0-d3ca4645ad9b · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.895961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0768739-4b97-4a00-8780-64afb5c31fe7 · outbound

This paper cites AgentServe: Algorithm-system co-design for efficient agentic AI serving on a consumer-grade GPU, 2026.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control AgentServe: Algorithm-system co-design for efficient agentic AI serving on a consumer-grade GPU, 2026

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:20:46.076765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1e4c7b8c-c9bc-41c4-a222-828eb8762f64 · outbound

This paper cites TokTier: Exact stateful CPU+GPU tokenization for agentic LLM serving, 2026.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control TokTier: Exact stateful CPU+GPU tokenization for agentic LLM serving, 2026

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.579198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0fde7dff-09ae-4281-b70f-3f2e15b5e8fe · outbound

This paper cites The smoke and full local run used the same GPU UUID and are not independent placements.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control The smoke and full local run used the same GPU UUID and are not independent placements

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.567953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 87016c91-2664-436e-a57d-0ac432a1f4ec · outbound

This paper cites Both external placements were ultimately retained.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Both external placements were ultimately retained

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.555198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation abd8b378-b2e7-4c66-a471-2e8e6d4f81a2 · outbound

This paper cites an unresolved cited work.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:20:46.542466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7c611aef-013e-4308-abb1-a5e0db41db94 · outbound

This paper cites Retained receipts support the successful execution and final resource absence.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Retained receipts support the successful execution and final resource absence

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.529915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 97ae7a51-1a68-418b-8aa0-ed528e4ab016 · outbound

This paper cites URL https://doi.org/10.1145/1798596.1798602.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control URL https://doi.org/10.1145/1798596.1798602

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-16T00:20:45.787126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b59c0f-abf6-4342-855f-cc7851e0e102 · outbound

This paper cites ISBN 978-1-939133-40-3.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control ISBN 978-1-939133-40-3

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.649304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1fc91ae-b65e-4387-a6ec-fb7e598efc57 · outbound

This paper cites Chapter 4.2, CUDA Graphs; accessed 2026-08-12.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Chapter 4.2, CUDA Graphs; accessed 2026-08-12

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:20:46.615250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.