Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning

TL;DR

Latent-DARM introduces a latent-space framework that combines discrete diffusion language models and autoregressive models to enhance reasoning and planning in multi-agent systems, achieving higher accuracy with less token usage.

Contribution

This paper presents Latent-DARM, a novel latent-space communication framework that effectively bridges DDLMs and ARMs for improved reasoning and collaboration.

Findings

Outperforms text-based interfaces on reasoning benchmarks.

Significantly improves accuracy on DART-5 and AIME2024.

Uses less than 2.2% of the token budget of state-of-the-art models.

Abstract

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete Diffusion Language Models (DDLMs) enable non-sequential, globally revisable generation and have shown strong planning capabilities, but their limited text fluency hinders direct collaboration with ARMs. We introduce Latent-DARM, a latent-space communication framework bridging DDLM (planners) and ARM (executors), maximizing collaborative benefits. Across mathematical, scientific, and commonsense reasoning benchmarks, Latent-DARM outperforms text-based interfaces on average, improving accuracy from 27.0% to 36.0% on DART-5 and from 0.0% to 14.0% on AIME2024. Latent-DARM approaches the results of state-of-the-art reasoning models while using less than 2.2% of its token budget. This work advances multi-agent collaboration among agents with heterogeneous models.