4‑bit Quantization Says It’s Safe—But Multi‑Turn LLM Agents Reveal Hidden Failure Spike
The paper shows that standard benchmark scores stay flat after 4‑bit post‑training quantization, yet error rates in multi‑turn, tool‑calling agents jump up to 2.5×, masking damage behind the error‑budget. Reducing the error budget or using per‑channel error diagnostics exposes the degradation, urging new reporting practices.