LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
An information-theoretic model for steganography.Information and Computation, 192(1):41–56, July 2004
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Maps cryptographic constructions to transformer architectures via threshold circuits and derives scaling laws for width and depth.
citing papers explorer
-
Voluntary Collusion with Secret Tools in Competing LLM Agents
LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
-
Exploring the Cryptographic Limits of Transformer Networks
Maps cryptographic constructions to transformer architectures via threshold circuits and derives scaling laws for width and depth.