Metraipolis › archive › dc_94d33ba16bae

Exploit More, Explore Smarter for Budget-Constrained Agentic Search — arXiv:2608.23848

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23848
License (as archived)
CC0-1.0
Archived
2026-10-18T06:36:38.090Z
SHA-256 of the archived text
6d52e794bcf2eaa7e82eb5a6f22551b827f46b01243e3000f3eb62c71bac58d5
Stable URL of this page
https://metraipolis.com/documento/dc_94d33ba16bae

How to cite

Exploit More, Explore Smarter for Budget-Constrained Agentic Search — arXiv:2608.23848 — arXiv (en), https://arxiv.org/abs/2608.23848 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_94d33ba16bae (Metraipolis archive dc_94d33ba16bae, sha256 6d52e794bcf2eaa7e82eb5a6f22551b827f46b01243e3000f3eb62c71bac58d5)
BibTeX
@misc{dc94d33ba16bae,
  title = {Exploit More, Explore Smarter for Budget-Constrained Agentic Search — arXiv:2608.23848},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23848},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_94d33ba16bae; sha256 6d52e794bcf2eaa7e82eb5a6f22551b827f46b01243e3000f3eb62c71bac58d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23848. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evaluation budget, because validation is expensive, generation requires multiple model calls, or both. In this regime, standard MCTS allocates budget poorly: exploration bonuses dominate at low visit counts, unpromising siblings are expanded before promising chains can deepen, and branching is independent of node quality. We introduce ExTS, a tree-search policy that treats expansion itself as a value-of-information decision. ExTS combines three mechanisms: discriminative reward shaping to separate candidates under narrow score distributions, a stochastic virtual child that estimates the value of creating a new branch from the parent's reward history, and quality-conditioned branching that expands only when a node's score justifies the budget cost. Across prompt optimization, code generation, molecular structure elucidation, and agentic workflow optimization, ExTS is competitive with or improves over task-specific tree-search baselines, with an average relative gain of +5.5% using a single fixed configuration. We further introduce pilot-run diagnostics that characterize what makes budget-constrained agentic search problems structurally different from one another, providing both understanding of the problem space and practical guidance for adaptation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23848 — 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 2026-10-18T06:28:52.322Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).