LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.
Routerdc: Query-based router by dual contrastive learning for assembling large language models.Advances in Neural Information Processing Systems, 37:66305–66328
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 3
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
baseline 3polarities
baseline 3representative citing papers
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
ModelLens learns a performance-aware latent space from 1.62M leaderboard records to rank unseen models on unseen datasets without forward passes on the target.
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
citing papers explorer
-
LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.
-
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
-
ModelLens: Finding the Best for Your Task from Myriads of Models
ModelLens learns a performance-aware latent space from 1.62M leaderboard records to rank unseen models on unseen datasets without forward passes on the target.
-
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.