arXiv Machine Learning June 16, 2026 By Ekasit Usaratniwart, Xilin Gao, Marc Ong, Youhei Akimoto

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 16236v1 Announce Type: new Abstract: Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training.

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 Machine Learning.

arXiv AI

Jun 2

Certificate-Guided Evaluation of Reinforcement Learning Generalization

arXiv:2606. 00840v1 Announce Type: new Abstract: This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks.

By Vignesh Subramanian, {\DJ}or{\dj}e \v{Z}ikeli\'c, Suguman Bansal

reinforcement-learning benchmarks

arXiv Machine Learning

Aug 28

Learning Generalizable Behaviors for Terminal Agents

The paper introduces the Agentic Compositional Generalization hypothesis, suggesting that reinforcement learning (RL) primarily refines high‑level decision‑making behaviors that orchestrate pre‑trained low‑level skills, rather than teaching new domain‑specific skills from scratch. It proposes River, a training recipe that enhances reward quality by filtering low‑quality synthetic environments and adding process‑level behavior regularization. Using River, RL‑trained agents outperform other open‑source 8B models on four terminal‑agent benchmarks, achieving significant gains with fewer than 30% of the training environments.

By Yihang Yao, Bo Pang, Xuan Phi Nguyen, Ding Zhao, Shafiq Joty, Semih Yavuz

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 5

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.

By Ranxu Zhang, Guinan Chen, Chenshaodong, Jinghao Lin, Xiaozhou Xu, Sunzhe, Yanyong Zhang, Chao Wang

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 15

Specifying Reward Functions for RL Without Environment Sampling

arXiv:2609.15544v1 Announce Type: cross Abstract: Enabling human stakeholders to specify reward functions that lead to their desired outcomes is a key challenge in deploying reinforcement learning ag...

By Stephane Hatgis-Kessell, W. Bradley Knox, Emma Brunskill

llms agents reinforcement-learning

arXiv Machine Learning

Jul 27

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.

By Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji

llms reinforcement-learning benchmarks

arXiv AI

Aug 17

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

arXiv:2608. 13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting.

By Yongqi Tong, Tan Li Hui Faith, Choy Zhen Wen Marcus, Zhou Jin, Kewei Fu, Jiang-Ming Yang, Jianshe Li, Xin Zhang

agents reinforcement-learning efficiency benchmarks safety

One email a morning, machine-written

Related stories

Certificate-Guided Evaluation of Reinforcement Learning Generalization

Learning Generalizable Behaviors for Terminal Agents

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

Specifying Reward Functions for RL Without Environment Sampling

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction