Paper Citation Record · LEDGER

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving

As of 17 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2608.00881.

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

pith.paper-citation-record.v1
2608.00881 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:20:28.126560Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

15 of 15 outbound references displayed

verified exact3
verified fuzzy3
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fcee5244-aade-4755-a62b-de3c156ca511 · outbound

This paper cites Cerebras Systems.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Cerebras Systems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.042776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6212f2b-ab92-45d0-b61c-ba6ecfac7e10 · outbound

This paper cites Dong, Y.; He, J.; Liu, S.; Hou, Y.; Du, D.; Xu, Z.; Yu, S.; Yang, B.; Xia, Y.; and Chen, H.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Dong, Y.; He, J.; Liu, S.; Hou, Y.; Du, D.; Xu, Z.; Yu, S.; Yang, B.; Xia, Y.; and Chen, H

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.049260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68ad4c18-9f3e-4deb-b9d2-1b92ef30b17a · outbound

This paper cites DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.058643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef164db-c4aa-4e34-9196-9a59286a5528 · outbound

This paper cites https://groq.com/blog/groq-first-generation-14nm-chip- just-got-a-6x-speed-boost-introducing-llama-3-1-70b- speculative-decoding-on-groqcloud.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving https://groq.com/blog/groq-first-generation-14nm-chip- just-got-a-6x-speed-boost-introducing-llama-3-1-70b- speculative-decoding-on-groqcloud

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:20:28.788478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a4451f9e-cce1-476c-8797-1c20ead880bc · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.070855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f343a156-fb42-46b3-9620-e90f31d17a6e · outbound

This paper cites SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:20:28.450297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ccf8705a-9a59-4885-b8d3-fe97b0647fc4 · outbound

This paper cites B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM Agents.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM Agents

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T15:20:28.418544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c86d98a5-44dd-4860-bd85-8598bcba39ea · outbound

This paper cites Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.094074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876c14b8-991e-4280-8222-c2699bed6ea6 · outbound

This paper cites https://github.com/tile-ai/TileRT.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving https://github.com/tile-ai/TileRT

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:20:28.764410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4895e392-b52d-4480-a26c-3c8a14becb5c · outbound

This paper cites Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.106900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 562f19fd-fd3e-4cdc-9cd7-fb5c2699c6b5 · outbound

This paper cites an unresolved cited work.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Unresolved cited work

Reference 15

Resolution: verified exact; raw_fallback, observed 2026-08-15T15:20:28.317394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03912eba-df7f-4079-ad78-093d621483d8 · outbound

This paper cites InNeurIPS 2022 Foundation Models for Decision Making Workshop.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving InNeurIPS 2022 Foundation Models for Decision Making Workshop

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:20:28.746581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation daea8a35-fa15-4927-b678-b09fd4d1a1dc · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.034075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 205d74d8-116b-431a-b2c4-9b81b6ae928e · outbound

This paper cites Speculative Actions: A Lossless Framework for Faster Agentic Systems.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving Speculative Actions: A Lossless Framework for Faster Agentic Systems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T15:20:28.119305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a0ee541-b6cb-4a0f-bd6a-009c2ae8fc6f · outbound

This paper cites SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

Reference 2026

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:20:28.723056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.