Enabling Agents to Communicate Entirely in Latent Space
This addresses a fundamental bottleneck in multi-agent AI collaboration by enabling more nuanced communication, though it's presented as a feasibility study rather than a production-ready solution.
The paper tackles the limitation of natural language communication between LLM-based agents by proposing Interlat, a paradigm for direct latent space communication using LLM hidden states. Experiments show Interlat outperforms chain-of-thought prompting and single-agent baselines, with compression further accelerating inference while maintaining competitive performance.
While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling rich, internal latent states into discrete tokens inherently limits the depth and nuance of information that can be transmitted, thereby hindering collaborative problem-solving. Inspired by human mind-reading, we propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the last hidden states of an LLM as a representation of its mind for direct transmission (termed latent communication). An additional compression process further compresses latent communication via entirely latent space reasoning. Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines, promoting more exploratory behavior and enabling genuine utilization of latent information. Further compression not only substantially accelerates inference but also maintains competitive performance through an efficient information-preserving mechanism. We position this work as a feasibility study of entirely latent space inter-agent communication, and our results highlight its potential, offering valuable insights for future research.