# Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals

arXiv: https://arxiv.org/abs/2604.07494 · HTML: https://mlsanity.com/paper/2604.07494/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [A Survey on Collaborative Mechanisms Between Large and Small Language Models](https://mlsanity.com/paper/2505.07460/) (2025)
- [Token-Level LLM Collaboration via FusionRoute](https://mlsanity.com/paper/2601.05106/) (2026)
- [Code Red: The Business Impact of Code Quality -- A Quantitative Study of 39 Proprietary Production Codebases](https://mlsanity.com/paper/2203.04374/) (2022)
- [Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics](https://mlsanity.com/paper/2601.02200/) (2026)

## Built on by (most cited first, 3 of 3)

- [TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing](https://mlsanity.com/paper/2605.18859/) (2026)
- [HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools](https://mlsanity.com/paper/2605.17106/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Context: AI coding agents route every task to a single frontier large language model (LLM), paying premium inference cost even when many tasks are routine. Objectives: We propose Triage, a framework that uses code health metrics -- indicators of software maintainability -- as a routing signal to assign each task to the cheapest model tier whose output passes the same verification gate as the expensive model. Methods: Triage defines three capability tiers (light, standard, heavy -- mirroring, e.g., Haiku, Sonnet, Opus) and routes tasks based on pre-computed code health sub-factors and task metadata. We design an evaluation comparing three routing policies on SWE-bench Lite (300 tasks across three model tiers): heuristic thresholds, a trained ML classifier, and a perfect-hindsight oracle. Results: We analytically derived two falsifiable conditions under which the tier-dependent asymmetry (medium LLMs benefit from clean code while frontier models do not) yields cost-effective routing: the light-tier pass rate on healthy code must exceed the inter-tier cost ratio, and code health must discriminate the required model tier with at least a small effect size (hatp ≥ 0.56). Conclusion: Triage transforms a diagnostic code quality metric into an actionable model-selection signal. We present a rigorous evaluation protocol to test the cost--quality trade-off and identify which code health sub-factors drive routing decisions.