Preprint2026
GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
Unknown
GraphThink uses task graphs to enhance LLM planning for long-horizon embodied tasks, with GRPO-based reward design.
0Aug 1, 2026
arXiv
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
10 papersPreprintarXiv.org2025
Bridging Offline and Online Reinforcement Learning for LLMs
Jack Lanchantin, Angelica Chen, Janice Lan, et al.
This paper compares offline, semi-online, and fully online RL finetuning methods for LLMs, finding online and semi-online DPO and GRPO variants perform similarly and outperform offline methods, with multi-tasking across verifiable and non-verifiable
22Jun 26, 2025Large Language ModelsReinforcement Learning
arXiv
PreprintarXiv.org2025
Group Sequence Policy Optimization
Chujie Zheng, Shixuan Liu, Mingze Li, et al.
GSPO defines sequence-level importance ratios and clipping for stable, efficient RL training of LLMs, outperforming GRPO and stabilizing MoE training.
627Jul 24, 2025Large Language ModelsReinforcement Learning
arXiv
Preprint2026
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
Introduces parameter-space exploration for LLM RL via Perturbed Parameter Policy Optimization (3PO), improving downstream performance over GRPO at similar FLOPs.
0Aug 10, 2026Reinforcement LearningReasoning
arXiv
PreprintarXiv.org2025
Scaling Reasoning in Diffusion LLMs via RL
Siyan Zhao, Devaansh Gupta, Qinqing Zheng, et al.
Proposes d1, a framework adapting pre-trained masked diffusion LLMs into reasoning models via masked SFT and a novel critic-free RL algorithm diffu-GRPO.
168Apr 16, 2025Large Language ModelsReinforcement Learning
arXiv
PreprintarXiv.org2025
A Deep Dive into RL for LLM Reasoning
Zihe Liu, Jiashun Liu, Yancheng He, et al.
This paper systematically reviews RL techniques for LLM reasoning, identifies a minimalist combination of two techniques that outperforms GRPO and DAPO.
54Aug 11, 2025Reinforcement LearningReasoning
arXiv
Preprint2026
Reinforcement Learning for Code Optimization
Pierre Chambon, Kunhao Zheng, Juliette Decugis, et al.
This paper addresses the failure of standard RL for code optimization by introducing a three-stage pipeline (DMC-Optim benchmark, reward composition, and adapted GRPO) that significantly improves speed while preserving correctness.
0Jul 28, 2026Reinforcement Learning
arXiv
PreprintarXiv.org2025
Geometric-Mean Policy Optimization
Yuzhong Zhao, Yue Liu, Junpeng Liu, et al.
GMPO improves GRPO stability by replacing arithmetic mean with geometric mean of token rewards, reducing outlier sensitivity and boosting reasoning performance.
95Jul 28, 2025Large Language ModelsReasoning
arXiv
Preprint2025
Adaptive Reasoning Model
Unknown
An adaptive reasoning model that selects reasoning formats based on task difficulty to balance performance and efficiency, trained with Ada-GRPO to prevent format collapse.
0May 1, 2025Reasoning
Preprint2026
ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents
Binjie Zhang, M. Shou
ReGRPO enhances tool-using agents by integrating reflection-guided correction into policy optimization, improving performance through iterative self-correction.
0Jun 1, 2026
arXiv