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. We introduce a causal audit that applies controlled mes
Record details
Published: 29 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy · Transparency
Retrieved: 30 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
arXiv cs.AI · 29 July 2026
Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks
arXiv red teaming query · 30 July 2026
"Nobody Did This": Contribution, Originality, and Accountability in Agent-Mediated Collaboration
arXiv cs.CY · 30 July 2026
Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm
arXiv · 28 July 2026
One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
arXiv cs.AI · 30 July 2026
Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels
arXiv cs.CY · 28 July 2026
How to cite this record
ethics.ai (29 July 2026), “Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM,” evidence record 14823, https://ethics.ai/record/14823 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.