arXiv AI July 14, 2026 By Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema, Sohee Yang, Wai-Chung Kwan, Xuanli He, Wenda Li, Pasquale Minervini, Eleonora Giunchiglia, Shay B. Cohen

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

Read the original on arXiv AI →

arXiv:2508. 21787v3 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward.

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 Machine Learning

Aug 11

Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond

arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.

By Zachary Horvitz, Raghav Singhal, Hao Zou, Carles Domingo-Enrich, Zhou Yu, Rajesh Ranganath, Kathleen McKeown

llms diffusion reinforcement-learning fine-tuning

arXiv AI

2d ago

ReHoPER: Receding-Horizon Planning for Enhanced Reasoning

ReHoPER is an inference‑only, zero‑shot method that enhances large language models’ reasoning by generating and answering intermediate questions along multiple paths before producing a final answer. It plans a horizon of candidate intermediate questions, selects one to answer, and replans based on the updated history. The approach is task‑agnostic, using generic instructions across datasets and models without labeled data or task‑specific prompt design, and it outperforms strong baselines on several datasets, notably achieving the largest gains on the new iLLC benchmark for compositional reasoning.

By Saeed Ahmadnia, Cornelia Caragea

llms benchmarks

arXiv AI

Sep 1

GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning

arXiv:2608.30632v1 Announce Type: cross Abstract: Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language...

By Outongyi Lv, Yuanwei Zhang, Xiaoqun Zhang

llms reinforcement-learning

arXiv AI

Jul 2

Predicting LLM Reasoning Performance with Small Proxy Model

arXiv:2509. 21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up.

By Woosung Koh, Juyoung Suk, Sungjun Han, Se-Young Yun, Jamin Shin

llms benchmarks safety

arXiv Machine Learning

Aug 11

Process Supervision of Confidence Margin for Calibrated LLM Reasoning

arXiv:2604. 23333v2 Announce Type: replace Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.

By Liaoyaqi Wang, Chunsheng Zuo, William Jurayj, Benjamin Van Durme, Anqi Liu

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

2d ago

Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains

arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm,...

By Haokai Ma, Lee Yan Zhen, Gang Yang, Yunxiang Chen, Yunshan Ma, Tat-Seng Chua, Ee-Chien Chang

llms reinforcement-learning efficiency benchmarks

One email a morning, machine-written

Related stories

Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond

ReHoPER: Receding-Horizon Planning for Enhanced Reasoning

GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning

Predicting LLM Reasoning Performance with Small Proxy Model

Process Supervision of Confidence Margin for Calibrated LLM Reasoning

Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains