Metraipolis › archive › dc_e9ec36d992ed
Progressive Content Refinement with Decaying Reward Joint LinUCB — arXiv:2608.06750
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06750
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:46:48.562Z
- SHA-256 of the archived text
283b4803072a40b7cc66e7c03f8a795185b9252f834f4f1e39578bf387bfe2d5- Stable URL of this page
https://metraipolis.com/documento/dc_e9ec36d992ed
How to cite
Progressive Content Refinement with Decaying Reward Joint LinUCB — arXiv:2608.06750 — arXiv (en), https://arxiv.org/abs/2608.06750 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9ec36d992ed (Metraipolis archive dc_e9ec36d992ed, sha256 283b4803072a40b7cc66e7c03f8a795185b9252f834f4f1e39578bf387bfe2d5)
BibTeX
@misc{dce9ec36d992ed,
title = {Progressive Content Refinement with Decaying Reward Joint LinUCB — arXiv:2608.06750},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06750},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9ec36d992ed; sha256 283b4803072a40b7cc66e7c03f8a795185b9252f834f4f1e39578bf387bfe2d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06750. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Iterative refinement has significantly enhanced Large Language Model (LLM) performance; however, existing methods ranging from feedback-based Self-Refine to traditional bandit approaches often rely on static options or overlook the saturation effect. This neglect leads to over-exploitation, where the continuous use of identical prompts or arms results in diminishing rewards over time. To address this challenge, we propose a novel contextual bandit algorithm that explicitly incorporates reward decay modeling. Utilizing an Expectation-Maximization (EM) algorithm, our method simultaneously estimates both arm-specific and decay parameters. Furthermore, by embedding prompts as arms, we facilitate the joint learning of arm values, distinguishing our approach from the traditional disjoint Linear Upper Confidence Bound (LinUCB) framework. Experimental results on Sentiment Reversal and GSM8K benchmarks demonstrate that our method achieves significant performance gains over strong baselines. Finally, our ablation study confirms that the integration of reward decay modeling within the bandit framework is crucial for mitigating over-exploitation and optimizing the iterative refinement process. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.06750 — 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 2026-10-19T09:46:37.215Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).