HM-ROUTER: Joint Model and Harness Routing for Agentic Systems

arXiv:2609.32213 · cs.LG, cs.CL · Submitted 2026-09-26 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/hmarkc/HM-Router

Terminology

• Benchmark — 44× in this paper · explained in 2 episodes
• Accuracy — 38× in this paper · explained in 1 episode
• Core — 14× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Sample Efficiency — 5× in this paper · explained in 4 episodes
• Agentic System — 4× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• AUC — 3× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• RouterBench: A Benchmark for Multi-LLM Routing System
• Meta-Harness: End-to-End Optimization of Model Harnesses
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• Agentic Routing: The Harness-Native Data Flywheel
• Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
• AutoHarness: improving LLM agents by automatically synthesizing a code harness
• RouteLLM: Learning to Route LLMs with Preference Data
• CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
• SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
• Agents' Last Exam
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• An Illusion of Progress? Assessing the Current State of Web Agents
• ReAct: Synergizing Reasoning and Acting in Language Models
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
• Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
• The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
• Agent-as-a-Router: Agentic Model Routing for Coding Tasks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks