Pith. sign in

REVIEW 5 cited by

MixLLM: Dynamic Routing in Mixed Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.18482 v1 pith:GD73VJE4 submitted 2025-02-09 cs.CL cs.AIcs.DBcs.IR

classification cs.CLcs.AIcs.DBcs.IR
keywords costlatencyqualityresponseroutingdynamicllmsmixllm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response quality and minimize cost and latency. However, the challenges involve: (1) dynamic trade-offs among quality, cost, and latency; (2) enabling continual learning in deployed systems; and (3) navigating a varying (e.g., new LLM addition or old LLM removal) set of LLM candidates over time. To bridge these gaps, we develop MixLLM, a dynamic contextual-bandit-based routing system for query-LLM assignment. Specifically, we first leverage query tags to enhance query embeddings for the routing task. Next, we design lightweight prediction models to estimate the response qualities and costs of queries over LLMs. We then devise a meta-decision maker to choose the query-LLM assignments to best tradeoff response quality, cost, and latency. Finally, the system benefits from continual training, allowing it to adapt to evolving queries and user feedback over time. Our extensive experiments show that MixLLM achieves the best trade-offs in response quality, cost, and latency (97.25% of GPT-4's quality at 24.18% of the cost under the time constraint).

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference

    cs.CL 2026-07 conditional novelty 6.0 of 10

    PyroDash lets a small model decide mid-generation to hand off once to a frozen LLM, achieving 64.04% accuracy (+6.36 points vs LLM) at lambda=0.05 and 96.4% lower estimated cost at lambda=0.6.

  2. Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Route-To-Reason learns to predict the accuracy and token usage of each model-strategy pair and routes every query to the pair that maximizes a tunable accuracy-cost score.

  3. Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives

    cs.LG 2025-06 reject novelty 5.0 of 10

    TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...

  4. Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A router-selector-generator LLM agent team with offline PPO and dual memories unifies feature selection and generation, reporting improved downstream performance on six tabular datasets.

  5. LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A product-of-experts decoder that blends a fine-tuned LLM's token probabilities with a gradient-searched sequence decoder produces more valid and stable feature transformations than either alone.

Pith tools