Paper Citation Record · LEDGER

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

As of 13 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2608.07583.

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

pith.paper-citation-record.v1
2608.07583 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T00:37:48.192088Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

27 of 27 outbound references displayed

verified exact3
verified fuzzy11
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 705b7712-206a-441f-9014-5b53621344a6 · outbound

This paper cites MasRouter: Learning to Route LLMs for Multi-Agent Systems.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough MasRouter: Learning to Route LLMs for Multi-Agent Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.058667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fceb62-7aef-4cec-8979-e48bd6b371ae · outbound

This paper cites Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.064617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d5c5a5-cfaf-4e82-99fb-24b96a808886 · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Why Do Multi-Agent LLM Systems Fail?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.070092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db13bba3-3583-45a2-88d2-ac089fd5ae4d · outbound

This paper cites OpenRCA: Can large language models locate the root cause of software failures?.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough OpenRCA: Can large language models locate the root cause of software failures?

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.323258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ab04955d-352f-4174-8410-304052e9d642 · outbound

This paper cites Where LLM agents fail and how they can learn from failures,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Where LLM agents fail and how they can learn from failures,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.081155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d397fe6e-2615-433d-8401-015e005d4267 · outbound

This paper cites Abduct, act, predict: Scaffolding causal inference for automated failure attribution in multi-agent systems,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Abduct, act, predict: Scaffolding causal inference for automated failure attribution in multi-agent systems,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.086418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835ade05-3372-4a0e-99aa-9134f18f2389 · outbound

This paper cites AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.092374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 051a4cf2-0b15-45f6-889d-01909edfcdeb · outbound

This paper cites Causal LLM routing: End-to-end regret minimization from observa- tional data,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Causal LLM routing: End-to-end regret minimization from observa- tional data,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.097876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf24fe4-8392-444b-8b14-111e0616b8e8 · outbound

This paper cites Universal Model Routing for Efficient LLM Inference.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Universal Model Routing for Efficient LLM Inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.103030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac553be-6103-4922-a81b-f6e215a305a8 · outbound

This paper cites RouterBench: A Benchmark for Multi-LLM Routing System.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough RouterBench: A Benchmark for Multi-LLM Routing System

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.108261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4c0a62-30f5-467c-9c23-dc67b3a82c28 · outbound

This paper cites Towards fair and comprehensive evaluation of routers in collaborative LLM systems,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Towards fair and comprehensive evaluation of routers in collaborative LLM systems,

Reference 11

Resolution: verified exact; raw_fallback, observed 2026-08-11T00:37:48.625181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1ca6baa5-b0ba-4c1e-88ce-ffd775181f81 · outbound

This paper cites When routing collapses: On the degenerate convergence of LLM routers,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough When routing collapses: On the degenerate convergence of LLM routers,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.119220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8738e3cf-c5d3-475a-aff3-14fa1707aff8 · outbound

This paper cites Predict responsibly: Improving fairness and accuracy by learning to defer,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Predict responsibly: Improving fairness and accuracy by learning to defer,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.305862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 765e47fb-1f5a-4cf1-b745-0b5f61498e34 · outbound

This paper cites Consistent estimators for learning to defer to an expert,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Consistent estimators for learning to defer to an expert,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.289333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dc5afed4-17d4-413c-823a-0ce2b3b860fe · outbound

This paper cites Learning to defer to multiple experts: Consistent surrogate losses, confidence calibration, and conformal ensembles,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Learning to defer to multiple experts: Consistent surrogate losses, confidence calibration, and conformal ensembles,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.272370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 40ccebb5-c127-4cda-9f1d-41247d3ee171 · outbound

This paper cites Measures of diver- sity in classifier ensembles and their relationship with the ensemble accuracy,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Measures of diver- sity in classifier ensembles and their relationship with the ensemble accuracy,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.255293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6d2c4401-ac26-4c09-aab3-23d3ce3e512f · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.143948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a4542f3-b0e1-4041-b16e-6903a4dfc430 · outbound

This paper cites Selective classification for deep neural networks,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Selective classification for deep neural networks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.237913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4725dc46-6bc6-46b0-8e3e-0cc7b3e9dd5d · outbound

This paper cites Proactive routing to interpretable surrogates with distribution-free safety guarantees,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Proactive routing to interpretable surrogates with distribution-free safety guarantees,

Reference 19

Resolution: verified exact; raw_fallback, observed 2026-08-11T00:37:48.439251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ecdb3c17-efd6-427f-ba9b-3647ca7e036f · outbound

This paper cites Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.158499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d20dd6a-0e53-4abe-abf5-fc9ead43d318 · outbound

This paper cites Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:37:48.326351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c077a9d5-74b4-4015-88ab-152697b5fb71 · outbound

This paper cites Why do AI agents systematically fail at cloud root cause analysis?.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Why do AI agents systematically fail at cloud root cause analysis?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T00:37:48.168475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6da002b-cd20-4341-becc-13e76373d53f · outbound

This paper cites Probability inequalities for the sum of independent random variables,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Probability inequalities for the sum of independent random variables,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.218661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d7839837-96f0-4993-a071-80b436da4f11 · outbound

This paper cites Boucheron, G.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Boucheron, G

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.199781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 90e77dca-abec-493c-9d98-0094575f7f8c · outbound

This paper cites Empirical Bernstein bounds and sample variance penalization,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Empirical Bernstein bounds and sample variance penalization,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.182653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d2e8a053-53df-496b-af57-d43d47c49801 · outbound

This paper cites Convergence of estimates under dimension- ality restrictions,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Convergence of estimates under dimension- ality restrictions,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.165496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 02c93ae1-9933-46df-95f6-ce1a0bc79969 · outbound

This paper cites Estimation des densit ´es: risque minimax,.

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough Estimation des densit ´es: risque minimax,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:37:49.148005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.