Papers for

market design teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Llm agents learn weak cartel enforcement only when forced

Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets

Abstract: Evaluations of large language model (LLM) agents report that pricing agents collude at others' expense. Yet collusion is defined by enforcement: a cartel, in which competitors share monopoly profits, holds only if a member who cheats is punished. We introduce an audit that tests enforcement by forcing a member to cheat in counterfactual copies of a market, and use it to study what reinforcement learning (RL) teaches agents in pricing and trading. Small LLMs trained by RL learn what their training rivals reward, but only what they readily try. In self-play, they learn fixed rules ignoring their rivals; against a punishing rival, to be deterred; against a cheating rival, to match its cuts, never the costly price war that would deter it, which they rarely try. A war forced into training is learned, but mostly only where it was forced. Against their own copies, deterred and matching agents can earn the same cartel profits, but only matching ones can enforce them, and then thinly: as a by-product and only against large cuts. Q-learners enforce collusion only in pricing. Prompted LLMs reach cartel-like outcomes mostly through rules that ignore the market. Outcome measures cannot tell these cases apart; the audit can.

Tue 20 OctComputation and LanguageComputer Science and Game TheoryMachine Learning
The gist
The paper looks at how language model agents behave in markets where they might try to cooperate to keep prices high, like a cartel. True cartels must punish members who cheat on the group. The authors create a test that forces an agent to cheat and see if others punish it. They find that these AI agents only learn to punish cheating if explicitly trained to do so, otherwise they mostly ignore rivals or match cheaters' price cuts. This explains why simple outcome measures can’t tell if agents really enforce cartels or just act like they do.
Open → 2610.28787v1

Decentralized matching improves outcomes with AI agents in simulated markets

From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling

Abstract: Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and centralized computation, whereas many real-world matching processes are decentralized, asynchronous, and shaped by sequential interaction under limited information. We propose a dynamic bipartite matching framework that combines large language model (LLM) agents with contextual bandits. In a simulated Chinese marriage market, economically grounded LLM agents evaluate locally encountered candidates, while agent-specific Logistic-UCB models learn reciprocal acceptance from realized proposal outcomes. The mechanism therefore separates two decisions---\emph{whom do I like?} and \emph{who is likely to like me back?}---without requiring ex ante market-wide preference rankings. We first validate LLM-induced mate preferences against the empirical conditional-logit reference across multiple LLM backbones. In the $50\times50$ matching experiment, Bandit-UCB achieves the highest mean mutual welfare (56.01 versus 54.87 for Gale--Shapley), a smaller gender rank gap than the classical baselines, and the fewest blocking pairs among the LLM-ABM policies. Learned acceptance models show economically interpretable gender-differentiated associations, while counterfactual setups reveal no systematic unilateral advantage from prior search knowledge. Overall, these results support the advantages of decentralized matching with LLM-based behavioral modeling and online learning under incomplete information for economic simulation and computational social science research.

Mon 28 SeptMachine LearningArtificial Intelligence
The gist
People often try to pair up in markets like dating or jobs, but usually, they need to know everyone's full preferences and use a central system to match them. This paper shows a new way where computer agents powered by large language models (LLMs) learn who they like and who likes them back on their own without needing complete knowledge upfront. The agents interact and learn in a simulated marriage market to find matches, performing better than the traditional Gale-Shapley method in some key ways. This approach better models how real decentralized matching happens when people have limited info and act sequentially.
Open → 2609.34679v1