Pith. sign in

REVIEW 9 cited by

Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems

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 2502.00409 v3 pith:XVHB66OT submitted 2025-02-01 cs.AI cs.CL

Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems

classification cs.AI cs.CL
keywords routingsystemsqueriesstrategiescostsresourcesurveyadaptive
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Model (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component, such as conversational agents, are usually designed with monolithic, static architectures that rely on a single, general-purpose LLM to handle all user queries. However, these systems may be inefficient as different queries may require different levels of reasoning, domain knowledge or pre-processing. While generalist LLMs (e.g. GPT-4o, Claude-Sonnet) perform well across a wide range of tasks, they may incur significant financial, energy and computational costs. These costs may be disproportionate for simpler queries, resulting in unnecessary resource utilisation. A routing mechanism can therefore be employed to route queries to more appropriate components, such as smaller or specialised models, thereby improving efficiency and optimising resource consumption. This survey aims to provide a comprehensive overview of routing strategies in LLM-based systems. Specifically, it reviews when, why, and how routing should be integrated into LLM pipelines to improve efficiency, scalability, and performance. We define the objectives to optimise, such as cost minimisation and performance maximisation, and discuss the timing of routing within the LLM workflow, whether it occurs before or after generation. We also detail the various implementation strategies, including similarity-based, supervised, reinforcement learning-based, and generative methods. Practical considerations such as industrial applications and current limitations are also examined, like standardising routing experiments, accounting for non-financial costs, and designing adaptive strategies. By formalising routing as a performance-cost optimisation problem, this survey provides tools and directions to guide future research and development of adaptive low-cost LLM-based systems.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

    cs.LG 2026-06 unverdicted novelty 7.0

    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.

  2. TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

    cs.LG 2026-05 accept novelty 7.0

    TwinRouterBench supplies step-level static evaluation with 970 prefixes and verified tiers plus a dynamic harness for live SWE-bench agent runs, enabling deterministic scoring for agentic LLM routing.

  3. TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

    cs.LG 2026-05 accept novelty 7.0

    TwinRouterBench supplies 970 execution-verified router prefixes across five datasets plus a live harness for 100 held-out SWE-bench cases, scoring routers on tier accuracy, trajectory success, and realized token cost ...

  4. Flexible Routing via Uncertainty Decomposition

    cs.LG 2026-05 unverdicted novelty 7.0

    A router that decomposes uncertainty to flexibly route queries between cheap models and oracles while providing regret bounds and supporting abstention in classification tasks with multiple annotations.

  5. Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers

    cs.LG 2025-05 conditional novelty 7.0

    A well-tuned kNN router matches or exceeds state-of-the-art learned routers on new standardized benchmarks spanning instruction, QA, reasoning, and the first multi-modal visual routing dataset, due to locality of mode...

  6. LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?

    cs.AI 2026-05 unverdicted novelty 6.0

    LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.

  7. Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training

    cs.AI 2026-05 conditional novelty 6.0

    Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant ...

  8. From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing

    cs.LG 2026-06 unverdicted novelty 5.0

    DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.

  9. Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance

    cs.AI 2026-05 unverdicted novelty 4.0

    Proposes a modular agentic architecture for educational LLMs with stage-specific modules to incorporate pedagogical advice and improve controllability over monolithic chatbots.