LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
American Economic Review 110, 10 (Oct
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Misspecified estimate-then-optimize pricing converges to supra-competitive prices when initial random explorations occur in similar ranges, reaching monopoly levels under symmetry.
In a repeated market-maker/taker game with endogenous price impact, projected stochastic gradient ascent by adaptive agents reaches a region of persistent overpricing in finite time.