Distilling Foundation Models for Agentic What-If Reasoning:Cost, Latency, and Governance in a Hybrid LLM+SLM Architecture

arXiv:2609.16091 · cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.LG

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 13 pages, 1 figure, 7 tables

Code: https://github.com/nitsourish/Model-Distillation-Age

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 36× in this paper · explained in 1 episode
• Benchmark — 34× in this paper · explained in 2 episodes
• Distillation — 31× in this paper · explained in 2 episodes
• AUC — 22× in this paper · explained in 2 episodes
• Fine-Tuning — 15× in this paper · explained in 5 episodes
• Foundation Model — 15× in this paper · explained in 3 episodes
• Foundation Models — 9× in this paper · explained in 7 episodes
• Ablation — 6× in this paper · explained in 1 episode
• In-Context Learning — 4× in this paper · explained in 4 episodes
• Knowledge Distillation — 4× in this paper · explained in 11 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Agentic Loop — 3× in this paper · explained in 1 episode
• Amortization — 3× in this paper · explained in 1 episode
• LLM judge — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Agentic Workflows — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 2× in this paper
• Activation Function — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• EU General Data Protection Regulation — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• LLM Orchestrator — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Post-Selection — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Distilling the Knowledge in a Neural Network
• Characterising Bias in Compressed Models
• In-Context Data Distillation with TabPFN
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

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