Conceptualization and experimentation of asset market with price manipulation

We study how AI agents form expectations and trade in experimental asset markets. Using a simulated open-call auction populated by autonomous Large Language Model (LLM) agents, we document three main findings. First, AI agents exhibit classic behavioral patterns: a pronounced disposition effect and recency-weighted extrapolative beliefs. Second, these individual-level patterns aggregate into equilibrium dynamics that replicate classic experimental findings (Smith et al., 1988), including the predictive power of excess demand for future prices and the positive relationship between disagreement and trading volume. Third, by analyzing the agents' reasoning text through a twenty-mechanism scoring framework, we show that targeted prompt interventions causally amplify or suppress specific behavioral mechanisms, significantly altering the magnitude of market bubbles.

Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, and time. We study this interpretation gap in a virtual exchange populated by ten role-conditioned language-model agents. The agents communicate, trade reference assets and futures, launch tokens, and manage concentrated-liquidity pools under prescriptive adversarial roles. We analyze eight 72-cycle trajectories across two time-blinded hourly replay paths, with a runner-side wallet policy enabled or disabled. The retained artifacts connect generated outgoing messages, policy events, balances, positions, and cycle-end market state. A focal reconstruction shows a launch--promotion--exit scenario realized across private coordination, public claims, follower positioning, repeatedly withheld exits, and a later non-blocking request aligned with a token balance change. Across policy-enabled runs, the gate withholds direct requests selectively; most policy-categorized candidates are flagged rather than blocked, while the surrounding interaction can continue. Repeated runs also show that category-level and within-trajectory relations can recur even when normalized score-change rankings do not. These findings motivate agent-behavior evaluation that links communication, authorization, and evolving state instead of treating individual transaction verdicts as complete safety judgments.

Some properties of so-called complex or collective systems can be observed to emerge from the interactions of elementary agents. This phenomenon, known as emergent behaviour, has long since been studied in the most diverse disciplines, with recent growing awareness from the formal methods community about the opportunity of opening up to seemingly distant disciplines with appropriate technology for computer-aided reasoning. Different peculiar elements of complexity make automated reasoning on these systems particularly challenging. We consider electronic financial markets to drive our discussion. We identify and structure the sources of complexity to tackle in order to provide computational support for the analysis of emergent phenomena. We refrain from evaluating the suitability of specific technical solutions or frameworks of preference, which would as usual require simplifying assumptions and divert from the actual phenomenon of interest. Rather, we elaborate on possible alternatives to handle some of the main technical aspects involved in automated analysis, while retaining a solid and concrete interpretation of the domain, and in doing so outline a more systematic research program for the formal specification and analysis of market mechanisms.