Tag
Introduces the Contagion Tensor and Coupling Amplification Factor (CAF) as a baseline-referenced, unitless ratio to quantify output-distribution coupling in multi-agent LLM systems, validated with real-API experiments on DeepSeek-Chat and GPT-4o-mini.
The paper introduces the Latent Bridge, a trainable continuous channel that couples a slow reasoning VLM (Qwen3-VL-8B-Thinking) and a fast reactive VLM (MiniCPM-o 4.5) for real-time game agents. Experiments on Atari games and MetaDrive show it matches or outperforms the text-based bridge while avoiding destructive interference when used alone.
This paper proposes a falsifiable applicability criterion for a training-free, fixed-length descriptor for multivariate time series based on time-lagged spectral embeddings, showing when it can be expected to work and validating it on multiple benchmarks.
This paper identifies a phase transition in language model scaling where below a critical parameter count, reasoning and truthfulness are anticorrelated, but above it they cooperate. It provides diagnostics and interventions for improving alignment across model families.