conftrace_

reward incentive

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

communication paraphrasing (1) multi-agent system (1) large language model (1) steganographic collusion (1) information hiding (1) llm safety (1) agent system (1) reinforcement learning (1)

Papers

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs IJCNLP 2025