Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bit

arXiv:2609.32042 · cs.CL · Submitted 2026-09-25 · Read on arXiv

cs.CL

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/JakubPrejzner/polagentbench

Terminology

• Quantization — 39× in this paper · explained in 12 episodes
• Scaffolding — 13× in this paper · explained in 3 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Distillation — 9× in this paper · explained in 2 episodes
• Pruning — 9× in this paper · explained in 4 episodes
• Failure Modes — 6× in this paper · explained in 3 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Agentic Task — 3× in this paper · explained in 1 episode
• Agentic Tasks — 3× in this paper · explained in 1 episode
• Decode — 3× in this paper · explained in 2 episodes
• Failure Taxonomy — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Edge Deployment — 1× in this paper · explained in 2 episodes
• Graceful Degradation — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Resource-Efficient Language Models: Quantization for Fast and Accessible Inference
• Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct
• An empirical study of LLaMA3 quantization: from LLMs to MLLMs
• Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
• How Does Quantization Affect Multilingual LLMs?
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
• Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling
• TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
• Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation
• Bielik 11B v2 Technical Report
• Bielik v3 Small: Technical Report
• Bielik 11B v3: Multilingual Large Language Model for European Languages
• Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language
• Compact Language Models via Pruning and Knowledge Distillation
• PLLuM: A Family of Polish Large Language Models
• Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering