RouteJudge introduces an open platform for preference-based evaluation of LLM routers via pairwise user comparisons, along with the ORBIT toolbox for standardized routing workflows.
Mixllm: Dynamic routing in mixed large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SeqRoute applies offline RL with CQL and Hindsight Budget Relabeling to sequential LLM routing under global budgets, claiming 6.0-73.5% cost reduction, maintained or improved quality, and under 1% bankruptcy rate.
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
citing papers explorer
-
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
RouteJudge introduces an open platform for preference-based evaluation of LLM routers via pairwise user comparisons, along with the ORBIT toolbox for standardized routing workflows.
-
SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning
SeqRoute applies offline RL with CQL and Hindsight Budget Relabeling to sequential LLM routing under global budgets, claiming 6.0-73.5% cost reduction, maintained or improved quality, and under 1% bankruptcy rate.
-
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.
-
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.