arXiv AI October 1, 2026 By Huaiyu Fu, Heng Cao, Hao Wang, Jian Ya, Tao Chen

Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents

The paper introduces Trajectory-guided Joint Policy Optimization (TJPO), a reinforcement‑learning framework that explicitly encourages diversity in the trajectories of large‑language‑model agents. By defining task‑specific trajectory descriptors, TJPO measures and optimizes diversity as a set‑level function, avoiding population‑based training. Experiments on Sokoban and ALFWorld demonstrate that TJPO yields diverse, interpretable behaviors while preserving strong task performance.

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 14

Trajectory First: A Curriculum for Discovering Diverse Policies

arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.

By Cornelius V. Braun, Sayantan Auddy, Marc Toussaint

agents reinforcement-learning robotics safety

arXiv AI

Aug 21

Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning

arXiv:2608. 19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL.

By Tanachai Anakewat, Takayuki Osa, Tatsuya Harada

reinforcement-learning robotics

arXiv Machine Learning

Jul 31

S-GRPO: Unified Post-Training for Large Vision-Language Models

arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).

By Yuming Yan, Kai Tang, Sihong Chen, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu

llms reinforcement-learning fine-tuning multimodal

arXiv Machine Learning

Jun 16

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

arXiv:2505. 09655v5 Announce Type: replace-cross Abstract: Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning.

By Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aristeidis Sotiras, Yalin Wang, Abolfazl Razi

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

arXiv Machine Learning

Aug 18

Temporal Logic Guided Universal Task Representations for Reinforcement Learning

arXiv:2608. 15509v1 Announce Type: cross Abstract: Task guided agents demonstrate strong performance in a wide range of complex tasks.

By Hao Zhang, Zhangli Zhou, Zhen Kan

agents reinforcement-learning robotics

One email a morning, machine-written

Related stories

Trajectory First: A Curriculum for Discovering Diverse Policies

Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning

S-GRPO: Unified Post-Training for Large Vision-Language Models

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Temporal Logic Guided Universal Task Representations for Reinforcement Learning