Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency
cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- The Faiss library
- Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
- When to Think Deeply: Inhibitory Deliberation for LLM Reasoning
- HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs
- Influence of Prompt Engineering on Small Language Models for Guarded Query Routing
- Qwen2.5 Technical Report
- Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents