LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
X., and Schulz, E
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.
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.
-
Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.