Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning

• URL: http://arxiv.org/abs/2606.10184v1
• Date: Mon, 08 Jun 2026 21:21:42 GMT
• Title: Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning
• Abstract summary: latent-reasoning models like Coconut feed continuous hidden states recurrently in place of discrete chain-of-thought tokens.<n>Applying group-relative reinforcement learning to continuous latent reasoning has proven difficult.<n>By applying a single Bernoulli mask held constant across all latent recurrence steps for a given rollout, we generate essential trajectory variance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - μ_r$ collapses to zero. This presents a structural challenge for latent-reasoning models like Coconut, which feed continuous hidden states recurrently in place of discrete chain-of-thought tokens. Because the latent phase is inherently deterministic given the parameters and prompt, multiple rollouts produce identical trajectories, stalling GRPO's progress. Consequently, applying group-relative reinforcement learning to continuous latent reasoning has proven difficult. To address this, we propose sourcing the necessary stochasticity through structured dropout. By applying a single Bernoulli mask held constant across all latent recurrence steps for a given rollout, we generate essential trajectory variance. This shared mask effectively treats each rollout as a posterior sample from a variational distribution over parameters, allowing GRPO to optimize the expected reward of a Bayesian model-average policy. We provide both theoretical justification for this method -- including unbiasedness, variance reduction, and the well-definedness of the latent gradient -- and empirical validation. On GSM8K, dropout-GRPO improves a Coconut baseline from $27.29\%$ to $29.01\%$ pass@1, demonstrating the viability of GRPO learning for latent-reasoning models. Our work positions this as a practical, theoretically grounded approach for post-training latent-reasoning LLMs.

Related papers

• Beyond Mode Collapse: Distribution Matching for Diverse Reasoning [69.88237286885065]
  On-policy reinforcement learning methods like GRPO suffer from mode collapse.<n>We show this stems from reverse KL minimization's mode-seeking behavior.<n>We propose DMPO, which prevents mode collapse through principled approximation of forward KL minimization.
  arXiv  Detail & Related papers  (2026-05-19T07:13:00Z)
• Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective [22.848847562976633]
  Existing methods face a fundamental bias-variance dilemma: token-level IS ratios, as adopted by PPO and GRPO, introduce bias by ignoring prefix state distribution mismatch.<n>We propose CTPO, which combines the cumulative token IS ratio with position-adaptive clipping that scales log-space clip bounds according to the natural $sqrtt$ growth of the cumulative log-ratio.
  arXiv  Detail & Related papers  (2026-05-08T06:35:02Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO [18.988527161000203]
  Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models.<n>We present a contrastive reformulation of GRPO, showing that the GRPO objective implicitly maximizes the margin between the policy ratios of correct and incorrect samples.<n>We propose Bilateral Context Conditioning (BICC), a mechanism that allows the model to cross-reference successful and failed reasoning traces.
  arXiv  Detail & Related papers  (2026-03-13T16:25:02Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off [34.80019950191864]
  We introduce a textbfdistribution-centric perspective for reinforcement learning.<n>We propose Distribution-Centric Policy Optimization (DCPO), which reformulates entropy regulation as distribution-level regularization.<n>Overall, DCPO replaces sample-levels with distribution-level principles, offering a theoretically grounded and flexible framework for exploration and a stronger EE trade-off.
  arXiv  Detail & Related papers  (2026-01-19T05:20:46Z)
• Delta-AI: Local objectives for amortized inference in sparse graphical models [64.5938437823851]
  We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. We illustrate $Delta$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.
  arXiv  Detail & Related papers  (2023-10-03T20:37:03Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)

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.