Metraipolis › archive › dc_d2b3e7cca044

AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization — arXiv:2609.39927

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39927
License (as archived)
CC0-1.0
Archived
2026-10-07T13:14:01.959Z
SHA-256 of the archived text
2f3bc764e20ea85c407723b41b639fbb62aa0581c2e40b76db2fd4194a972ef6
Stable URL of this page
https://metraipolis.com/documento/dc_d2b3e7cca044

How to cite

AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization — arXiv:2609.39927 — arXiv (en), https://arxiv.org/abs/2609.39927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2b3e7cca044 (Metraipolis archive dc_d2b3e7cca044, sha256 2f3bc764e20ea85c407723b41b639fbb62aa0581c2e40b76db2fd4194a972ef6)
BibTeX
@misc{dcd2b3e7cca044,
  title = {AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization — arXiv:2609.39927},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39927},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2b3e7cca044; sha256 2f3bc764e20ea85c407723b41b639fbb62aa0581c2e40b76db2fd4194a972ef6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompts on task examples and use the resulting feedback to guide prompt revisions through reflection. However, when feedback selection does not account for the prompt's weaknesses, these revisions may improve performance on selected examples without yielding broader task improvements. To address this issue, we propose AdaGEPA, an adaptive feedback-allocation method that uses the prompt's performance and task structure to select examples for the next prompt revision. Our method replaces at most one example in each feedback minibatch to target an identified weakness while preserving the remaining feedback context. Across our main experiments on six downstream benchmarks, AdaGEPA achieves higher mean validation scores than non-adaptive feedback selection under matched rollout budgets. AdaGEPA also finds high-performing prompts earlier across several tasks. In the initial Schema-Guided Dialogue (SGD) study, its half-budget prompts outperform the non-adaptive baseline's full-budget prompts in joint goal accuracy on new dialogues from services seen and unseen during search. Overall, our findings highlight the potential of adaptive feedback allocation to improve both the effectiveness and rollout-budget efficiency of reflective prompt optimization.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.39927 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:44:51.871Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).