arXiv AI June 4, 2026 By Peiming Li, Zhiyuan Hu, Yang Tang, Shiyu Li, Xi Chen

Aligning Deep Implicit Preferences by Learning to Reason Defensively

arXiv:2510. 11194v3 Announce Type: replace Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 11

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

arXiv:2608. 08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference.

By Juncheng Dong, Ding Tong, Ishan Gupta, Yuyan Wang

llms agents reinforcement-learning safety

arXiv Machine Learning

Jun 30

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.

By Pei-Chi Pan, Yingbin Liang, Sen Lin

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 29

ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning

arXiv:2607. 25369v1 Announce Type: new Abstract: Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users.

By Jiaqi Zhang, Tong Chen, Junliang Yu, Quoc Viet Hung Nguyen, Hongzhi Yin

agents fine-tuning

arXiv Machine Learning

Jun 15

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

arXiv:2505. 04671v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance.

By Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Guoliang Li, Bin Wu, Wenchao Zhou

llms reinforcement-learning safety data-engineering

arXiv AI

Jun 29

PreferThinker: Reasoning-based Personalized Image Preference Assessment

arXiv:2511. 00609v4 Announce Type: replace Abstract: Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information.

By Shengqi Xu, Xinpeng Zhou, Yabo Zhang, Ming Liu, Tao Liang, Tianyu Zhang, Yalong Bai, Zuxuan Wu, Wangmeng Zuo

reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 9

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.

By Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian, Nihal Sharma, Rizal Fathony, Nam H Nguyen, C. Bayan Bruss, Amrit Singh Bedi, Furong Huang

safety

Related stories

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

PreferThinker: Reasoning-based Personalized Image Preference Assessment

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning