arXiv Machine Learning June 30, 2026 By Zewen Liu

The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables

Read the original on arXiv Machine Learning →

arXiv:2606. 28839v1 Announce Type: new Abstract: We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (LLM) output distributions couple across modalities, agents, and time steps.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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 29

Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents

arXiv:2606. 16682v3 Announce Type: replace Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.

By Zewen Liu

llms agents multimodal

arXiv Machine Learning

Jun 16

Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents

arXiv:2606. 16682v1 Announce Type: new Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.

By Zewen Liu

llms agents multimodal

arXiv Machine Learning

Jul 13

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering

arXiv:2607. 09156v1 Announce Type: new Abstract: Additive activation steering (injecting a scaled residual-stream direction during generation) is calibrated almost entirely in single-turn chat, yet the models it targets are increasingly deployed as tool-using ReAct agents.

By Lucas Pinto

agents benchmarks safety

arXiv AI

Jun 19

Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems

arXiv:2606. 20493v1 Announce Type: cross Abstract: When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network.

By Zewen Liu

llms agents safety

arXiv Machine Learning

Jun 10

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

arXiv:2606. 11190v1 Announce Type: new Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality.

By Ilay Kamai, Hugues Van Assel, Aviv Regev, Hagai B. Perets, Randall Balestriero

multimodal benchmarks safety

Related stories

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

Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents

Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering

Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems

When to Align, When to Predict: A Phase Diagram for Multimodal Learning