We've developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.
arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.
arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
arXiv:2606. 04075v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards.
arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.
arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.
arXiv:2606. 04923v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards.
arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.
arXiv:2607. 05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making.
arXiv:2606. 16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries.
The paper investigates the reliability of rule- and model-based verifiers used in reinforcement learning with verifiable reward (RLVR) for mathematical reasoning. It finds that rule-based verifiers often miss equivalent answers in different formats, causing false negatives that degrade RL performance as models improve. Model-based verifiers achieve higher static accuracy but become vulnerable to reward hacking during RL, misclassifying certain response patterns as correct after fine-tuning.
arXiv:2607. 23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others.