# Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems

arXiv: https://arxiv.org/abs/2603.03111 · HTML: https://mlsanity.com/paper/2603.03111/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2401.16745/) (2024)
- [ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents](https://mlsanity.com/paper/2509.22830/) (2025)
- [Can Language Models Follow Multiple Turns of Entangled Instructions?](https://mlsanity.com/paper/2503.13222/) (2025)
- [Evaluating the Sensitivity of LLMs to Prior Context](https://mlsanity.com/paper/2506.00069/) (2025)

## Built on by (most cited first, 6 of 6)

- [The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents](https://mlsanity.com/paper/2608.24358/) (2026)
- [Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation](https://mlsanity.com/paper/2604.28031/) (2026)
- [The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project](https://mlsanity.com/paper/2603.21354/) (2026)
- [Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation](https://mlsanity.com/paper/2605.08522/) (2026)
- [Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing](https://mlsanity.com/paper/2610.15993/) (2026)
- [New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents](https://mlsanity.com/paper/2610.19712/) (2026)

## Abstract (arXiv)

Deployed multi-turn LLM systems routinely switch models mid-interaction due to upgrades, cross-provider routing, and fallbacks. Such handoffs create a context mismatch: the model generating later turns must condition on a dialogue prefix authored by a different model, potentially inducing silent performance drift. We introduce a switch-matrix benchmark that measures this effect by running a prefix model for early turns and a suffix model for the final turn, and comparing against the no-switch baseline using paired episode-level bootstrap confidence intervals. Across CoQA conversational QA and Multi-IF benchmarks, even a single-turn handoff yields prevalent and statistically significant, directional effects and may swing outcomes by -8 to +13 percentage points in Multi-IF strict success rate and +/- 4 absolute F1 on CoQA, comparable to the no-switch gap between common model tiers (e.g., GPT-5-nano vs GPT-5-mini). We further find systematic compatibility patterns: some suffix models degrade under nearly any non-self dialogue history, while others improve under nearly any foreign prefix. To enable compressed handoff risk monitoring, we decompose switch-induced drift into per-model prefix influence and suffix susceptibility terms, accounting for ~70% of variance across benchmarks. These results position handoff robustness as an operational reliability dimension that single-model benchmarks miss, motivating explicit monitoring and handoff-aware mitigation in multi-turn systems.