Iterate on an LLM, Serve on an SLM
cs.AI, cs.MA
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- A General Language Assistant as a Laboratory for Alignment
- Non-Determinism of "Deterministic" LLM Settings
- Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems
- Small Language Models are the Future of Agentic AI
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Distilling the Knowledge in a Neural Network
- LoRA: Low-Rank Adaptation of Large Language Models
- Distilling LLM Agent into Small Models with Retrieval and Code Tools
- ToolACE: Winning the Points of LLM Function Calling
- APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets
- Small Language Models: Survey, Measurements, and Insights
- Orca: Progressive Learning from Complex Explanation Traces of GPT-4
- RouteLLM: Learning to Route LLMs with Preference Data
- Gorilla: Large Language Model Connected with Massive APIs
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Learning by Distilling Context
- Qwen3 Technical Report
- AgentTuning: Enabling Generalized Agent Abilities for LLMs
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