Metraipolis › archive › dc_32f388485aae

arXiv 2610.31667: Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.31667
License (as archived)
CC-BY-4.0
Archived
2026-10-23T05:16:17.468Z
SHA-256 of the archived text
d59e723bfdeecd864c331fb13a0a3cc8c1cf3a5578b70db1e90555000139e9d8
Stable URL of this page
https://metraipolis.com/documento/dc_32f388485aae

How to cite

arXiv 2610.31667: Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning — Metraipolis archive, https://arxiv.org/abs/2610.31667 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_32f388485aae (Metraipolis archive dc_32f388485aae, sha256 d59e723bfdeecd864c331fb13a0a3cc8c1cf3a5578b70db1e90555000139e9d8)
BibTeX
@misc{dc32f388485aae,
  title = {arXiv 2610.31667: Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.31667},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_32f388485aae; sha256 d59e723bfdeecd864c331fb13a0a3cc8c1cf3a5578b70db1e90555000139e9d8},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.31667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of candidate solutions in the hope of finding at least one correct solution. Running all candidate solutions to completion can be computationally demanding, so recent work prunes the candidate pool after generating only a short prefix, committing further computation only to the surviving candidates. Existing pruning strategies divide broadly into two categories: Quality-based methods assign a score to each partial solution and discard those predicted to ultimately lead to an incorrect final solution, while diversity-based methods select partial solutions that follow different reasoning trajectories and are therefore likely to cover different final solutions. The tension between these two objectives is an instance of exploration versus exploitation, yet little to no prior work on pruning exposes this trade-off directly, let alone optimizes it. In this paper, we introduce a pruning procedure that addresses this trade-off directly by optimizing pass@$k$ over the selected solution pool. In particular, it chooses the pool to maximize the probability that at least one of its partial solutions, when continued to completion, yields a correct answer. Because this objective simultaneously rewards high-quality partial solutions and penalizes redundancy among them, quality and diversity are naturally balanced by the criterion itself rather than through separate ad-hoc design choices. On eight open-weight reasoning models, our method outperforms existing quality-based and diversity-based pruning strategies. The gains are particularly pronounced when the pruning procedure keeps a moderate number of partial solutions for continued generation, highlighting the value of directly balancing quality and diversity during pruning.

Articolo: «Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning» — Salmani, Mahdi; Javanmard, Adel; Gupta, Devansh; Razaviyayn, Meisam (2026-10-22), arXiv:2610.31667, categoria cs.AI (intelligenza artificiale).
Fonte: https://arxiv.org/abs/2610.31667
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-23T05:16:12Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.