mlsanityData to 7 Oct 2026

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

arXiv 2603.09184 ↗First posted 10 Mar 2026cs.LG cs.AIcited by 1

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 30 of its 36 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

30 of 36 references.

References · 30

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  9. 2025Large Language Diffusion Modelscited by 872
  10. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  11. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  12. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
18 more
  1. 2020Aligning AI With Shared Human Valuescited by 706
  2. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  3. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  4. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  5. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 385
  6. 2024Discrete Flow Matchingcited by 301
  7. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 211
  8. 2024The pitfalls of next-token predictioncited by 156
  9. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planningcited by 135
  10. 2024DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solvingcited by 92
  11. 2025Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thoughtcited by 73
  12. 2025A Survey on Latent Reasoningcited by 71
  13. 2025Generalized Interpolating Discrete Diffusioncited by 68
  14. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  15. 2025Theoretical Benefit and Limitation of Diffusion Language Modelcited by 46
  16. 2025Fine-Tuning Masked Diffusion for Provable Self-Correctioncited by 39
  17. 2025Optimal Inference Schedules for Masked Diffusion Modelscited by 25
  18. 2025Multi-Agent Collaborative Framework For Math Problem Generationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Plan-and-Patch: Diffusion Language Models for Agentic Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
  2. 2025Latent Collaboration in Multi-Agent Systems
  3. 2026Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
  4. 2026Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
  5. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
  6. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
  7. 2026Adaptive Latent Agentic Reasoning
  8. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents