Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression

2026-06-28

AI Summary

This work addresses the instability and lack of interpretability in continuous latent-space reasoning, which arises from the mismatch between continuous internal states and discrete symbolic supervision signals. To resolve this, the authors propose Discrete Latent Reasoning (DLR), a novel approach that transforms continuous latent representations into interpretable discrete tokens for the first time. DLR constructs a discrete latent vocabulary by integrating text-to-image rendering, visual feature extraction, and clustering, and unifies the autoregressive modeling of natural language and latent tokens. Inspired by render-and-compress principles, the method achieves state-of-the-art performance across two model families—Qwen3-VL and LLaMA-3—and five reasoning benchmarks, compressing reasoning sequences by up to 20× while preserving semantic fidelity and enabling human-interpretable reasoning trajectories.

Abstract

Large language models achieve high reasoning performance via explicit chain-of-thought and reinforcement learning, but require long output sequences and extended inference time. Latent reasoning reduces this cost by shifting computation into a latent space; however, continuous latent methods are hard to train, suffering from unstable and uninterpretable reasoning trajectories. We argue these issues stem from a misalignment between continuous-space reasoning and discrete symbolic supervision, as continuous states lack explicit anchors for step-by-step alignment. To resolve this, we propose \textbf{Discrete Latent Reasoning~(DLR)}, the first method that converts continuous latent states into explicit discrete tokens. Inspired by render-based compression, we render textual chains of thought into images, extract visual features, and construct a discrete latent vocabulary via clustering-based fine-tuning. Expanding the vocabulary and output head enables standard autoregressive modeling over both natural language and latent tokens, supporting pretraining alignment, SFT, and RL. Experiments on five reasoning benchmarks and two model series~(Qwen3-VL and LLaMA-3) confirm that \textbf{DLR} outperforms prior latent reasoning baselines with up to \textbf{20$\times$ compression}. Furthermore, the learned latent trajectories retain an interpretable semantic structure. Overall, discrete latent tokens provide a controllable and interpretable basis for efficient latent reasoning.

Problem

• continuous latent reasoning
• discrete symbolic supervision
• interpretable reasoning
• latent space alignment
• unstable reasoning trajectories

Innovation

• Discrete Latent Reasoning
• Rendered Compression
• Latent Tokenization
• Interpretable Reasoning
• Chain-of-Thought Compression