Beyond Tier Labels: Role- and Deployment-Dependent Model Substitution in Multi-Call LLM Workflows
4.20T1 sourcearXiv cs.MA
Source record
Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2608.09155.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryThe paper argues that model substitution in multi-call LLM workflows should be treated as a deployment-conditioned action rather than dictated by tier labels. It proposes a predicate-action factorization evaluated across solve-merge-verify workflows with 8-64 calls and multiple model ladders, showing that the same substitution has sharply different value depending on role and scale.
Why it mattersChallenges the default 'stronger model = better' routing heuristic in multi-call LLM systems by showing a model's value depends on its position in a dependent computation, not just its tier.
Cited by
No citations on record.