arXiv Machine Learning August 18, 2026 By Michael Lingzhi Li, Shixiang Zhu

Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation

Read the original on arXiv Machine Learning →

arXiv:2409. 11535v3 Announce Type: replace Abstract: Many decision-support systems recommend actions by optimizing measurable objectives, even when a human decision-maker retains final authority and considers additional criteria that are difficult to specify in advance.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

Hugging Face Trending Papers

Jun 2

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity.

llms agents reinforcement-learning fine-tuning

arXiv AI

Jun 3

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

arXiv:2606. 03962v1 Announce Type: cross Abstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward.

By Anthony GX-Chen, Ankit Anand, Gheorghe Comanici, Zaheer Abbas, Eser Ayg\"un, David Smalling, Shibl Mourad, Doina Precup, Andr\'e Barreto, Mark Rowland

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 2

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

arXiv:2509. 03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits.

By Imad Aouali, Otmane Sakhi

arXiv Machine Learning

Jul 31

On-Policy and Off-Policy Learning for Large Action Spaces

arXiv:2607. 28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback.

By Imad Aouali

agents diffusion safety

arXiv AI

Jul 7

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

arXiv:2603. 27044v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space.

By Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

diffusion reinforcement-learning benchmarks

arXiv AI

Jun 4

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences

arXiv:2605. 07724v2 Announce Type: replace-cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that objective.

By Ali Falahati, Mohammad Mohammadi Amiri, Kate Larson, Lukasz Golab

safety

Related stories

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation

On-Policy and Off-Policy Learning for Large Action Spaces

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences