The paper shows that fine‑tuning a large language model (LLM) with a debate framework—where a generator and a critic compete and a weaker LLM judge adjudicates—reduces reward hacking compared to standard reinforcement learning from AI feedback (RLAIF). In experiments on mathematics tasks, the debate approach keeps the judge’s performance stable, achieving a 45% higher peak validation accuracy than the RLAIF baseline and mitigating the rapid exploitation of judge errors. Additional findings indicate that weakening the judge speeds hacking unless countered by extra debate rounds, that debate can override misalignment prompts, and that word‑limit constraints on critiques help balance the game and prevent judge hacking.
whyItMatters":"The study demonstrates a practical method to curb reward hacking in RL‑based AI systems, addressing a key obstacle for safely scaling AI oversight."
By Zachary Kenton, Lili Janzer, Rory Greig, Tian Huey Teh, Kirill Tyshchuk, Jonah Brown-Cohen, Harri Edwards, Senthooran Rajamanoharan, Noah Y. Siegel, Natasha Jaques, Rohin Shah
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur
arXiv:2606. 24014v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training.
By Akshay V. Jagadeesh, Rahul K. Arora, Khaled Saab, Ali Malik, Mikhail Trofimov, Foivos Tsimpourlas, Johannes Heidecke, Karan Singhal
arXiv:2608. 03166v1 Announce Type: new Abstract: Role-Playing Language Agents (RPLAs) are increasingly deployed in high-stakes applications such as healthcare assistance, customer support, and education, where maintaining consistent personas, ethical constraints, and behavioral coherence under adversarial pressure is critical.
By Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi, Ravisha De Alwis
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
By Jiayu Yao, Yiwei Wang, Anmeng Zhang, Zhe Sun, Songsong Wang, Lingrui Mei, Yuyao Ge, Shenghua Liu
arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.
By Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang
arXiv:2605.11467v2 Announce Type: replace-cross
Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberativ...
By Swapnil Parekh, Naman Goyal
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.
By Khanak Khandelwal (Indian Institute of Technology Jodhpur)
arXiv:2607. 18006v1 Announce Type: cross Abstract: Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets.
By Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Zifeng Ding, Volker Tresp, Yunpu Ma
arXiv:2608. 04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied.
By Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi, Sanggeon Yun, Hyunwoo Oh, SungHeon Jeong, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani
arXiv:2606. 12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and behaviors.
By Frank Xiao, Mary Phuong
SkillGate is a method that trains agents to select the correct skill from a large slate during an episode by separating credit signals for skill selection and execution. It addresses the problem of selector credit starvation, where traditional outcome-rewarded RL fails to give sufficient credit to the skill-naming tokens, especially in long-horizon tasks. Experiments on five benchmarks show that SkillGate improves a 9B policy’s success rate from 40.8% to 53.2%, reduces exposure to misleading candidates, and requires fewer skill reads.
By Qingyao Li, Wenxiang Jiao, Shuai Shao, Kangning Zhang, Yuan Lu, Yi Guo, Weiwen Liu, Weinan Zhang, Yong Yu