LEPO: Latent Reasoning Policy Optimization for Large Language Models

• URL: http://arxiv.org/abs/2604.17892v2
• Date: Tue, 21 Apr 2026 03:14:50 GMT
• Title: LEPO: Latent Reasoning Policy Optimization for Large Language Models
• Abstract summary: We introduce controllableity into latent reasoning via Gumbel-Softmax.<n>We propose textbfunderlineLatent Rtextbfunderlineeasoning textbfunderlinePolicy textbfunderlineOptimization(textbfLEPO)<n>In tests, LEPO significantly outperforms existing RL methods for discrete and latent reasoning.
• Score: 11.032175358561162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference, failing to discover diverse reasoning paths. To bridge the gap, we inject controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). Building on this, we propose \textbf{\underline{L}}atent R\textbf{\underline{e}}asoning \textbf{\underline{P}}olicy \textbf{\underline{O}}ptimization~(\textbf{LEPO}), a novel framework that applies RL directly to continuous latent representations. Specifically, in rollout stage, LEPO maintains stochasticity to enable diverse trajectory sampling, while in optimization stage, LEPO constructs a unified gradient estimation for both latent representations and discrete tokens. Extensive experiments show that LEPO significantly outperforms existing RL methods for discrete and latent reasoning.

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)
• Reinforcement Learning with Promising Tokens for Large Language Models [11.420715885411925]
  Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs)<n>We introduce Reinforcement Learning with Promising Tokens (R), a framework that mitigates the action space issue by decoupling strategic decision-making from token generation.
  arXiv  Detail & Related papers  (2026-02-03T07:08:06Z)
• Beyond Mode Elicitation: Diversity-Preserving Reinforcement Learning via Latent Diffusion Reasoner [23.232437167002406]
  Latent Diffusion Reasoning with Reinforcement Learning (LaDi-RL) is a framework that conducts exploration directly in a continuous latent space.<n>By modeling exploration via guided diffusion, multi-step denoising distributesity and preserves multiple coexisting solution modes.<n> Experiments on code generation and mathematical reasoning benchmarks demonstrate consistent improvements in both pass@1 and pass@k over discrete RL.
  arXiv  Detail & Related papers  (2026-02-02T06:26:31Z)
• Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization [1.974921946982281]
  Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Recent studies question whether RL genuinely expands reasoning capacity or merely aligns existing latent capabilities, arguing that exploration remains confined within the pre-trained model's low-rank bias manifold.<n>We propose Manifold-Reshaping Policy Optimization (MRPO), a geometric framework designed to fundamentally restructure the inference space of LLMs.
  arXiv  Detail & Related papers  (2026-01-30T05:38:44Z)
• Parallel Latent Reasoning for Sequential Recommendation [23.624137982116867]
  We propose PLR, a novel framework for exploring multiple diverse reasoning trajectories simultaneously.<n>PLR constructs parallel reasoning streams through learnable trigger tokens in continuous latent space.<n>Experiments on three real-world datasets demonstrate that PLR substantially outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-01-06T16:25:48Z)
• Parallel Test-Time Scaling for Latent Reasoning Models [58.428340345068214]
  Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs)<n>Recent advances in latent reasoning, where intermediate reasoning unfolds in continuous vector spaces, offer a more efficient alternative to explicit Chain-of-Thought.<n>This work enables parallel TTS for latent reasoning models by addressing the above issues.
  arXiv  Detail & Related papers  (2025-10-09T03:33:00Z)
• Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization [5.674809920704963]
  Latent Thought Policy Optimization enhances LLM reasoning entirely at test time.<n>Experiments show that LTPO not only matches or surpasses strong baselines on standard tasks but also demonstrates remarkable robustness where others fail.<n>Most notably, on highly challenging AIME benchmarks where existing latent reasoning baselines collapse to near-zero accuracy, LTPO delivers substantial improvements.
  arXiv  Detail & Related papers  (2025-10-05T12:50:39Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Revisiting LLM Reasoning via Information Bottleneck [57.519119962528166]
  Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR)<n>We present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle.<n>We propose IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable.
  arXiv  Detail & Related papers  (2025-07-24T13:14:25Z)
• Hybrid Latent Reasoning via Reinforcement Learning [50.6763762323985]
  We explore latent reasoning by leveraging the capabilities of large language models (LLMs) via reinforcement learning (RL)<n>We introduce hybrid reasoning policy optimization (HRPO), an RL-based hybrid latent reasoning approach that integrates prior hidden states into sampled tokens with a learnable gating mechanism.<n>HRPO-trained LLMs remain interpretable and exhibit intriguing behaviors like cross-lingual patterns and shorter completion lengths.
  arXiv  Detail & Related papers  (2025-05-24T01:26:16Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes [99.26864533035454]
  We study offline reinforcement learning (RL) in partially observable Markov decision processes. We propose the underlineProxy variable underlinePessimistic underlinePolicy underlineOptimization (textttP3O) algorithm. textttP3O is the first provably efficient offline RL algorithm for POMDPs with a confounded dataset.
  arXiv  Detail & Related papers  (2022-05-26T19:13:55Z)

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.