arXiv AI October 31, 2026 By Rituraj Sharma, Weiyuan Chen, Noah Provenzano, Tu Vu

PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference

PRISM is a new inference algorithm for DEEPTHINK systems that uses a Process Reward Model (PRM) to guide step‑level verification, resampling, and aggregation of candidate solutions. By concentrating computation on higher‑quality reasoning while preserving diversity, PRISM improves performance on complex mathematical and scientific tasks, achieving 90.0%, 75.4%, and 71.4% on AIME25, HMMT25, and GPQA Diamond with gpt‑oss‑20b and outperforming larger models. The method also provides consistent net‑directional correction during refinement and remains accurate even when the initial population has few correct candidates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 28

DeepLook: Deeper Thinking with Lookahead

arXiv:2607. 22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reasoning tasks than parameter scaling alone.

By Tingxin Yang, Zefeng Wang, Mengyue Wang, Xingcheng Zhou, Yunpu Ma

llms benchmarks

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv AI

Jul 21

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.

By Jaehun Jung, Seungju Han, Ximing Lu, Skyler Hallinan, David Acuna, Shrimai Prabhumoye, Mostafa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

llms benchmarks

arXiv AI

Sep 1

Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide

arXiv:2608.30051v1 Announce Type: new Abstract: Process reward models (PRMs) provide dense step-level guidance for search-based reasoning, enabling inference-time compute to be allocated toward promi...

By Taejong Joo, Diego Klabjan

fine-tuning efficiency

arXiv Machine Learning

Jun 5

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

arXiv:2604. 08477v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved reasoning in formal domains such as mathematics and code, but extending these gains beyond STEM remains challenging.

By Ashima Suvarna, Kendrick Phan, Mehrab Beikzadeh, Hritik Bansal, Saadia Gabriel

llms reinforcement-learning benchmarks

arXiv AI

Jun 10

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

arXiv:2606. 09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable.

By Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake, Thomas L. Griffiths

llms agents fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

DeepLook: Deeper Thinking with Lookahead

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models