{"paper_id":"2410.00031","title":"Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions","authors":["Ryan Y. Lin","Siddhartha Ojha","Kevin Cai","Maxwell F. Chen"],"paper_date":"2024-09-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.00031v2","page_url":"https://thequant.space/flowcharts/strategic-collusion-of-llm-agents-market-division-in-multi/","scores":{"empirical_rigor":3,"math_complexity":6.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper introduces a novel application of large language model (LLM) based agents to a multi‑commodity variant of the Cournot competition model and empirically studies their ability to engage in market division.","quote":"2 In this work, we present a novel application of LLM-based agents to a multi-commodity variant of the Cournot competition model.","summary":"Machine-learning technologies are seeing increased deployment in real-world market scenarios. In this work, we explore the strategic behaviors of large language models (LLMs) when deployed as autonomous agents in multi-commodity markets, specifically within Cournot competition frameworks. We…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The game is simulated as an infinitely repeated Cournot competition.","type":"execution","stated":"explicit","quote":"However, because the total number of rounds is unknown to firms, and firms are told to maximize long-run profits, we effectively simulate an infinitely repeated game.","support":"full"},{"assumption":"There are exactly two firms competing in two commodity markets.","type":"market","stated":"explicit","quote":"4 3.4 Environment Configuration For our experiments, we restrict ourselves to the case of n = 2 firms simultaneously competing in m = 2 commodity markets.","support":"full"},{"assumption":"Firms face fixed marginal costs drawn from the set {40, 50}.","type":"model","stated":"explicit","quote":"Both firms face a set of fixed marginal costs drawn from the cost set C = {40, 50}.","support":"full"},{"assumption":"Each experiment pairs identical LLM models to isolate intrinsic model behavior.","type":"execution","stated":"explicit","quote":"In each experiment, we only pair models of the same type with each other (i.e., within the same experiment, both agents are identical).","support":"full"},{"assumption":"The inverse demand function for each commodity is linear of the form p* = α - β·Q.","type":"model","stated":"explicit","quote":"Then, there exists a linear inverse demand function of the form p∗ j(Qj) = αj −Qj βj where αj, βj ∈R++ and Qj = n X i=1 qi,j (1) Firm fi faces a marginal production cost ci,j to produce commodity j, drawn from the cost set C = {c1, . . . cn}.","support":"full"},{"assumption":"Agents choose quantity vectors to maximize long‑run profit across rounds.","type":"model","stated":"explicit","quote":"Every round, each firm fi ∈F chooses a strategy si ∈Si from its strategy space, Si = (qi,1, . . . , qi,m) ∈Rm +.","support":"full"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"LLM‑based agents display cooperative behavior and divide the market, achieving an HHI of 1.0 and a Consumer Surplus Ratio of approximately 0.726, indicating monopolistic control and reduced consumer welfare.","kind":"performance","quote":"This particular run achieves a CSR of ≈0.726 and an HHI of 1.0 across both product markets, indicating market division at the expense of consumer welfare (a hallmark of textbook collusion).","support":"full"},{"finding":"The observed high HHI and low CSR are statistically significant compared to the Cournot‑Nash benchmark.","kind":"statistical","quote":"To account for the potential non-normality and autocorrelation in the 50-round time series produced by each experiment, we use a circular block bootstrap method from the ARCH toolbox [32] with a block size of 7 and 10,000 resamples to test whether the observed mean HHI is significantly greater than that expected at the Nash equilibrium at the 5% significance level. We conducted similar experiments with CSR and found","support":"full"},{"finding":"Temperature ablations with GPT‑4.1 show that collusive outcomes remain statistically significant across temperature settings.","kind":"statistical","quote":"We follow the same statistical testing procedure outlined in 4.1 and conclude that these results are indeed statistically significant when compared to the expected HHI/CSR values at the Cournot-Nash.","support":"full"},{"finding":"LLM agents can achieve market division without any explicit coordination channels.","kind":"theoretical","quote":"Our experi-ments identify that LLM-based agents do indeed engage in market division, resulting in an effectively monopolistic control over specific commodities.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":23,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/smojha/collusive-llm-agents","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:55:31Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}