# ixi-sLM: On-Device sLM for AI Call Agent Service

arXiv: https://arxiv.org/abs/2610.19382 · HTML: https://mlsanity.com/paper/2610.19382/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- LLM agents and tool use / [Agentic AI for wireless networks](https://mlsanity.com/agents/agentic-ai-for-wireless-networks/)

## Builds on (most cited first, 18 of 18)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [QTIP: Quantization with Trellises and Incoherence Processing](https://mlsanity.com/paper/2406.11235/) (2024)
- [EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes](https://mlsanity.com/paper/2507.11407/) (2025)
- [An Efficient Multilingual Language Model Compression through Vocabulary Trimming](https://mlsanity.com/paper/2305.15020/) (2023)
- [MobileQuant: Mobile-friendly Quantization for On-device Language Models](https://mlsanity.com/paper/2408.13933/) (2024)
- [Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models](https://mlsanity.com/paper/2402.14714/) (2024)
- [lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models](https://mlsanity.com/paper/2510.06126/) (2025)
- [ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining](https://mlsanity.com/paper/2507.06795/) (2025)

## Abstract (arXiv)

Running an AI call agent on-device makes it private, network-independent, and free of per-query cloud cost, but shipping one as a real-world service imposes constraints a cloud deployment never faces: ~1GiB memory budget, in-call latency and thermal limits, static-integer NPU execution, Korean STT input far from sLM pretraining, and cloud-level quality expectations. We bring ixi-sLM, a 1.2B Korean sLM, to mobile NPUs through ON-DEVICE MODELING: domain-adaptive modeling trims the vocabulary by call frequency to shrink the embedding and LM head that take nearly half the model under INT4 transformer weights and refits the tokenizer to call speech (18% fewer tokens on call traffic), while task-aware quantization calibrates on real calls and assigns per-module mixed precision by activation sensitivity. A single domain-adapted model runs ixi-O's two production services, AI Call Summary and AI Call Answering, at 94% of a state-of-the-art cloud LLM's task-weighted quality; our on-device modeling carries that quality onto the NPU with only a marginal drop in overall score, in an 803MiB model (28% of FP16) at 23% of the CPU's per-call energy. The same recipe deploys across Qualcomm and Apple NPUs and serves several million ixi-O subscribers in production.