Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/waldiez/slm-callsite-eval
Sources
- Small Language Models are the Future of Agentic AI
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Gemma 4 Technical Report
- RouterBench: A Benchmark for Multi-LLM Routing System
- Small Language Models: Survey, Measurements, and Insights
- RouteLLM: Learning to Route LLMs with Preference Data
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems