arXiv AI

Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication

The paper investigates whether diffusion language model agents can exchange hidden messages via their continuous denoising states. By compressing a sender’s state into four dense vectors, the receiver can incorporate this information while preserving its own context. Experiments on tasks such as Tiny-A2D, Dream-7B, and QASC show that removing or substituting the message significantly degrades performance, and that a single late transfer can outperform multiple exchanges.

Hugging Face Trending Papers

Jul 29

Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM

Latent communication in large language model (LLM)-based multi-agent systems (MAS) transmits continuous internal representations instead of text, but greater representational capacity does not establish that the receiver uses task-relevant information. End-task performance alone also cannot reveal whether an observed effect depends on message presence, content generated for the evaluated example, or information supplied by a separate agent.

llms agents

arXiv AI

Jul 31

Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM

arXiv:2607. 26773v1 Announce Type: new Abstract: Latent communication in large language model (LLM)-based multi-agent systems (MAS) transmits continuous internal representations instead of text, but greater representational capacity does not establish that the receiver uses task-relevant information.

By Huixiang Zhang, Mahzabeen Emu

llms agents

arXiv AI

Jul 20

Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models

arXiv:2607. 15893v1 Announce Type: cross Abstract: While the internal mechanisms of autoregressive (AR) transformers have been studied extensively, much less is known about diffusion language models (DLMs), an emerging alternative that generates text by iterative denoising.

By Andy Catruna, Emilian Radoi

llms rag diffusion

arXiv Computation and Language

Oct 22

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse

arXiv:2602.02133v3 Announce Type: replace-cross Abstract: Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$...

By Moongyu Jeon, Sangwoo Shin, BumJun Kim, Kyelim Lee, Albert No

llms diffusion

arXiv Computation and Language

Oct 15

Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models

arXiv:2610.19696v1 Announce Type: new Abstract: Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate thro...

By Xin Li, Mengbing Liu, Hao Jiang, Xin Gao, Annan Wang, Xingwei Qu, Yichi Zhang, Chau Yuen

llms agents fine-tuning

arXiv AI

Oct 1

Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents

arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding,...

By Jiacheng Qiu, Christopher E. Mower, Jan Peters, Haitham Bou-Ammar, Matthieu Zimmer

llms agents diffusion robotics benchmarks

arXiv AI

Jun 19

How Transparent is DiffusionGemma?

arXiv:2606. 20560v1 Announce Type: cross Abstract: LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors.

By Joshua Engels, Callum McDougall, Bilal Chughtai, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue, Jo\~ao Gabriel Lopes de Oliveira, Rohin Shah, Neel Nanda

llms diffusion safety

arXiv Machine Learning

Jul 3

BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems

arXiv:2607. 01600v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as communicating agents, does inter-agent communication cause outputs to converge?

By Zewen Liu

llms agents

arXiv Machine Learning

Jun 9

Continuous Language Diffusion as a Decoder-Interface Problem

arXiv:2606. 08810v1 Announce Type: cross Abstract: Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diffusion language models can generate fluent text from them.

By Zhicheng Du, Lan Ma

llms rag diffusion

arXiv Machine Learning

Jun 15

Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens

arXiv:2606. 14620v1 Announce Type: new Abstract: Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measured.

By Ali Asaria, Tony Salomone, Deep Gandhi

llms diffusion safety

arXiv AI

Aug 7

Answer First, Reason Later: Commitment Order in Diffusion LLMs

arXiv:2608. 05687v1 Announce Type: cross Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding.

By Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Hwiyeong Lee, Taesup Kim

llms diffusion

arXiv AI

Aug 25

Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models

The paper studies how the order in which tokens are committed in masked diffusion language models affects accuracy. It finds that when the final answer is committed before the preceding reasoning (an answer‑first trajectory), accuracy can suffer compared to unrestricted decoding, especially on tasks like GSM8K and MATH‑500. Experiments with controlled token positions show that delaying the answer token can improve performance, indicating that commitment order influences the context and output allocation of the model.

By Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Hwiyeong Lee, Taesup Kim

llms diffusion

Related stories