SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning

• URL: http://arxiv.org/abs/2602.01062v1
• Date: Sun, 01 Feb 2026 07:13:20 GMT
• Title: SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
• Authors: Chenyi Li, Yuan Zhang, Bo Wang, Guoqing Ma, Wei Tang, Haoyang Huang, Nan Duan,
• Abstract summary: We introduce a set level diversity objective defined over sampled trajectories using kernelized similarity.<n>Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization.<n>Experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.
• Score: 50.93295951454092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. However, such improvements often come with reduced outcome diversity, where the model concentrates probability mass on a narrow set of solutions. Motivated by diminishing-returns principles, we introduce a set level diversity objective defined over sampled trajectories using kernelized similarity. Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization. We further investigate the contribution of a single trajectory to language model diversity within a distribution perturbation framework. This analysis theoretically confirms a monotonicity property, proving that rarer trajectories yield consistently higher marginal contributions to the global diversity. Extensive experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.

Related papers

• The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving [57.652356955571065]
  State-of-the-art large language model (LLM) pipelines rely on bootstrapped reasoning loops.<n>We analyze how this design choice is sensitive to the collapse of the model's distribution over reasoning paths.<n>We introduce Distributional Creative Reasoning (DCR), a unified variational objective that casts training as gradient flow through probability measures on solution traces.
  arXiv  Detail & Related papers  (2026-01-02T17:10:31Z)
• Beyond Monolithic Rewards: A Hybrid and Multi-Aspect Reward Optimization for MLLM Alignment [1.8552770604791606]
  We propose a hybrid reward modeling framework that integrates complementary reward paradigms.<n>We show consistent improvements across different multimodal benchmarks when applying hybrid and multi-aspect reward modeling.<n>Our best performing model in the 3B family achieves an overall average improvement of 9.5% across general and math reasoning tasks.
  arXiv  Detail & Related papers  (2025-10-06T18:53:23Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion [0.8594140167290097]
  SPREAD is a generative framework based on Denoising Diffusion Probabilistic Models (DDPMs)<n>It learns a conditional diffusion process over points sampled from the decision space.<n>It refines candidates via a sampling scheme that uses an adaptive multiple gradient descent-inspired update for fast convergence.
  arXiv  Detail & Related papers  (2025-09-25T12:09:37Z)
• MAPO: Mixed Advantage Policy Optimization [120.96975697212065]
  We propose an easy but effective GRPO strategy, Mixed Advantage Policy Optimization (MAPO)<n>We reveal that the trajectory appears with different certainty and propose the advantage percent deviation for samples with high-certainty trajectories.
  arXiv  Detail & Related papers  (2025-09-23T09:37:16Z)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization [64.08326521234228]
  We propose a preference-guided diffusion model for offline multi-objective optimization.<n>Our guidance is a preference model trained to predict the probability that one design dominates another.<n>Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions.
  arXiv  Detail & Related papers  (2025-03-21T16:49:38Z)
• Learning Dynamic Representations via An Optimally-Weighted Maximum Mean Discrepancy Optimization Framework for Continual Learning [16.10753846850319]
  Continual learning allows models to persistently acquire and retain information.<n> catastrophic forgetting can severely impair model performance.<n>We introduce a novel framework termed Optimally-Weighted Mean Discrepancy (OWMMD), which imposes penalties on representation alterations.
  arXiv  Detail & Related papers  (2025-01-21T13:33:45Z)
• Comparative Analysis of Indicators for Multiobjective Diversity Optimization [0.2144088660722956]
  We discuss different diversity indicators from the perspective of indicator-based evolutionary algorithms (IBEA) with multiple objectives. We examine theoretical, computational, and practical properties of these indicators, such as monotonicity in species. We present new theorems -- including a proof of the NP-hardness of the Riesz s-Energy Subset Selection Problem.
  arXiv  Detail & Related papers  (2024-10-24T16:40:36Z)
• Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques [65.55451717632317]
  We study Preference-Based Multi-Agent Reinforcement Learning (PbMARL)<n>We identify the Nash equilibrium from a preference-only offline dataset in general-sum games.<n>Our findings underscore the multifaceted approach required for PbMARL.
  arXiv  Detail & Related papers  (2024-09-01T13:14:41Z)
• Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning [20.491176017183044]
  This paper tackles the multi-objective reinforcement learning (MORL) problem. It introduces an innovative actor-critic algorithm named MOAC which finds a policy by iteratively making trade-offs among conflicting reward signals.
  arXiv  Detail & Related papers  (2024-05-05T23:52:57Z)
• Distribution-Dependent Rates for Multi-Distribution Learning [26.38831409926518]
  Recent multi-distribution learning framework tackles this objective in a dynamic interaction with the environment. We provide distribution-dependent guarantees in the MDL regime, that scale with suboptimality gaps and result in superior dependence on the sample size. We devise an adaptive optimistic algorithm, LCB-DR, that showcases enhanced dependence on the gaps, mirroring the contrast between uniform and optimistic allocation in the multi-armed bandit literature.
  arXiv  Detail & Related papers  (2023-12-20T15:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.