arXiv Machine Learning July 31, 2026 By Jiwon Jang, Kisu Yang, Heuiseok Lim, Hyunwoo Park

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

Read the original on arXiv Machine Learning →

arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 10

Quantization Damage Is Multiplicative, Not Additive

arXiv:2608. 06564v1 Announce Type: new Abstract: Quantization is how large language models are actually deployed, and below four bits it is known to hurt.

By Zekun Wu, Swati Dhiman, Adriano Koshiyama

llms agents efficiency benchmarks safety

arXiv Machine Learning

Jul 15

Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate

arXiv:2607. 12266v1 Announce Type: new Abstract: Mixed-precision quantization must decide which parts of a model to keep at higher precision.

By Joshua Hill

efficiency

arXiv Machine Learning

Jul 21

Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding

arXiv:2607. 16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token.

By Anik Jha

llms agents fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 19

Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

arXiv:2606. 19558v1 Announce Type: new Abstract: Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality.

By Milo\v{s} Nikoli\'c, Ali Hadi Zadeh, Enrique Torres Sanchez, Andreas Moshovos

llms efficiency benchmarks

arXiv AI

Jun 10

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

arXiv:2606. 09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact.

By Bruce Changlong Xu, Adarsh Kumarappan, Mu Zhou

llms efficiency benchmarks safety

arXiv Machine Learning

Aug 11

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

arXiv:2608. 06564v2 Announce Type: replace Abstract: Quantization is how large language models are actually deployed, and below four bits it hurts.

By Zekun Wu, Swati Dhiman, Adriano Koshiyama

llms agents efficiency benchmarks safety

Related stories

Quantization Damage Is Multiplicative, Not Additive

Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate

Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding

Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them