We have 3 of 26 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Overall, the findings show that long-horizon interaction can reshape how agents coordinate in ways that create safety risks, and restricting the amount and scope of interaction history available to agents reduces collusion.
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewa...
Context-induced tail risks concealed by aggregate accuracy are revealed, motivating per-example reliability evaluation of language models.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
