AI Paper Atlas

Research map / Large language models / Alignment and preferences

TAMPO: Task- and Model-Aware Automatic Prompt Optimization for Auto-Routing in LLM-based Systems

Yuejun Jiao, Jun Xia, Yanxin Yang, Yonghao Yang, Hao Shen, Mingsong Chen

ICML 2026 · Large language models › Alignment and preferences · approach: DPO design choices

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace online iterative APO (APE/OPRO) with a single-pass conditional policyTAMPO · reasoning taskslatency (ms): 2098 (APE) -> 285 (latency-priority TAMPO)Improved
condition prompt generation on model metadata (task- and model-aware) instead of task-onlyRLPrompt vs TAMPO · reasoning tasksworst-case accuracy (%): 37.4 (RLPrompt) -> 39.7 (TAMPO quality)Improved
use preference vector to prioritise qualityTAMPO · reasoning tasksaverage accuracy (%): 40.0 (Static) -> 48.4Improved
prioritise token efficiency via preference vectorTAMPO · reasoning taskstokens: 131 (Static) -> 21Improved
use model-aware reward model instead of model-agnostic reward model (ablation)uncertainty-aware reward model · heterogeneity-aware datasetKendall's tau / NDCGImproved
add Gaussian NLL uncertainty term and epistemic penalty to an MSE-only reward model (ablation)reward model · MMLU degraded promptfinal reward vs actual accuracy 0.12: 0.85 -> 0.37Improved
generalise to unseen task and unseen modelTAMPO · AQuA + Gemma-1Baccuracy (%): 26.7 -> 30.6 (vs Static)Improved
quantise models from FP16 to INT8TAMPO quality-focused · heterogeneous modelsaccuracyNo clear effect
use few-shot prompting instead of zero-shotStatic · reasoning tasksaverage accuracy (%): 40.0 -> 36.8Hurt

Later papers that compared with this method

1 later accepted paper reports TAMPO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy