Skip to content
← Back to explorer

LLM Router: Rethinking Routing with Prefill Activations

Tanay Varshney, Annie Surla, Michelle Xu, Gomathy Venkata Krishnan, Maximilian Jeblick, David Austin, Neal Vaidya, Davide Onofrio · Mar 21, 2026 · Citations: 0

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model. While existing routers rely on semantic query features, they often fail to capture model-specific failures or intrinsic task difficulty. We instead study routing via internal prefill activations. Our key idea, Encoder-Target Decoupling, separates the model that produces the predictive signal (the Encoder) from the model whose correctness is being estimated (the Target), allowing open-weight encoders to predict the performance of closed-source target models. We evaluate layerwise geometric probes, finding that Fisher Separability (J) effectively identifies informative layers, supported by Effective Dimensionality (d_eff) diagnostics. We then utilize a SharedTrunkNet, a joint multi-output MLP that predicts simultaneous correctness probabilities across candidate models using concatenated prefill features. In our experiments, SharedTrunkNet consistently outperforms semantic baselines. At its best, SharedTrunkNet closes 45.58% of the gap between the strongest standalone model and the oracle while achieving 74.31% cost savings relative to the most expensive model. These results demonstrate that prefill activations provide a robust routing signal, establishing mechanistic routing as a high-performance alternative to purely semantic selection.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This paper looks adjacent to evaluation work, but not like a strong protocol reference.
  • The available metadata is too thin to trust this as a primary source.
  • The abstract does not clearly name benchmarks or metrics.

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 35%

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Metadata summary

LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model.
  • While existing routers rely on semantic query features, they often fail to capture model-specific failures or intrinsic task difficulty.
  • We instead study routing via internal prefill activations.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Research Summary

Contribution Summary

  • LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model.
  • We evaluate layerwise geometric probes, finding that Fisher Separability (J) effectively identifies informative layers, supported by Effective Dimensionality (d_eff) diagnostics.
  • At its best, SharedTrunkNet closes 45.58% of the gap between the strongest standalone model and the oracle while achieving 74.31% cost savings relative to the most expensive model.

Why It Matters For Eval

  • LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.