The paper introduces PrefMind, an online dual‑agent reinforcement learning framework that jointly trains a response Generator and a preference Critic to explicitly learn and apply human preference judgments. By having the agents discuss and correct each other’s evaluations of candidate responses, PrefMind embeds preference understanding directly into the generation process rather than relying solely on a scalar reward model. Experiments on models of varying sizes demonstrate gains in both preference judgment accuracy and downstream response quality.
arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.
arXiv:2606. 01123v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback.
arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.
arXiv:2605.08703v2 Announce Type: replace Abstract: Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference da...
The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.
arXiv:2506. 13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback.
arXiv:2607. 10601v1 Announce Type: new Abstract: Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation.
arXiv:2607. 01830v1 Announce Type: new Abstract: Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks.
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator.
The paper introduces a method for learning heterogeneous, individually conditioned utility functions—termed individuated utility—by leveraging rational choice theory. It presents a multi-stage architecture that estimates these functions from multimodal data and evaluates it on a large dataset of aesthetic judgments about automotive wheel designs. Results show that individuated models outperform universal utility models and foundation baselines, indicating that annotator disagreement reflects meaningful preference diversity.