LAD: Learning Advantage Distribution for Reasoning

• URL: http://arxiv.org/abs/2602.20132v1
• Date: Mon, 23 Feb 2026 18:44:10 GMT
• Title: LAD: Learning Advantage Distribution for Reasoning
• Authors: Wendi Li, Sharon Li,
• Abstract summary: We introduce Learning Advantage Distributions, a distribution-matching framework that replaces advantage with learning advantage-induced distribution.<n>We show that LAD reliably improves both accuracy and generative diversity.<n> Experiments on math and code reasoning tasks show that LAD reliably improves both accuracy and generative diversity.
• Score: 11.179134756179998
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning trajectories, thereby limiting diversity and exploration. To address this issue, we introduce Learning Advantage Distributions (LAD), a distribution-matching framework that replaces advantage maximization with learning the advantage-induced distribution. By establishing the equivalence between the optimal policy update and an advantage-based target distribution, we derive a practical LAD objective formulated as minimizing an $f$-divergence between the policy-induced and advantage-induced distributions. This yields a gradient update that increases likelihood for high-advantage responses while suppressing over-confident probability growth, preventing collapse without requiring auxiliary entropy regularization. LAD incurs no extra training cost compared to GRPO and scales naturally to LLM post-training. In a controlled bandit setting, LAD faithfully recovers the multimodal advantage distribution, validating the theoretical formulation. Experiments on math and code reasoning tasks across several LLM backbones show that LAD reliably improves both accuracy and generative diversity.

Related papers

• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity [13.211627219720796]
  Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning.<n>We argue that RL implicitly optimize the "mode-seeking" or "zero-forcing" Reverse KL to a target distribution causing the model to concentrate mass on certain high-probability regions of the target while others.<n>In this work, we instead begin from an explicit target distribution, obtained by filtering out incorrect answers while neglecting the relative probabilities of correct ones.
  arXiv  Detail & Related papers  (2025-12-05T18:56:40Z)
• Data-regularized Reinforcement Learning for Diffusion Models at Scale [99.01056178660538]
  We introduce Data-regularized Diffusion Reinforcement Learning ( DDRL), a novel framework that uses the forward KL divergence to anchor the policy to an off-policy data distribution.<n>With over a million GPU hours of experiments and ten thousand double-blind evaluations, we demonstrate that DDRL significantly improves rewards while alleviating the reward hacking seen in RLs.
  arXiv  Detail & Related papers  (2025-12-03T23:45:07Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• FlowRL: Matching Reward Distributions for LLM Reasoning [69.88820066093798]
  We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL)<n>We transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution.
  arXiv  Detail & Related papers  (2025-09-18T17:56:36Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [26.274786600234876]
  The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but amplify safety concerns. RLHF has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. DPO has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified
  arXiv  Detail & Related papers  (2023-09-28T08:29:44Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

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.