Not a Monolith: Lab-Level Divergence in the Cooperative Equilibria of Chinese Frontier LLM Agents
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
Does the cooperative bias documented for Western frontier LLM agents extend to a different alignment lineage, and should the Chinese models that embody it be treated as a single bloc or as distinct laboratories? We study four frontier-tier Chinese models - DeepSeek V4 Pro, Qwen3-Max, Kimi K2.5 and GLM-5.1 - in an evolutionary Iterated Prisoner's Dilemma, under a design that removes a confound present in prior work. Rather than letting each model convert its own natural-language strategies into code, which entangles strategic disposition with coding ability, we hold the converter fixed (GPT-5.4 Mini) across all labs, so every cross-lab comparison is a comparison of generation alone. We run the full protocol: all-play-all tournaments and a Moran process at n=500 runs per condition, across three prompt styles and four population regimes. Two pre-registered hypotheses are evaluated. H6 (not monolithic) is supported: the four labs differ significantly in aggressive-equilibrium proportion, P_A running from 1% for Qwen3-Max to 9% for DeepSeek V4 Pro, with four of six pairwise comparisons surviving Holm-Bonferroni. The spread across the four labs (P_A range 8pp) is larger than the difference between the Chinese and Western ecosystems' mean P_A (5.0% vs 5.0%): on this measure, within-ecosystem variation exceeds the East-West gap. H5 (cooperative-bias generality) is consistent but qualified: a cooperative plurality holds in 6 of 12 lab-prompt combinations against the 9 of 12 reported for Western models, a difference we do not treat as firm, since the count rests on Cooperative-Neutral near-ties and rises to 9/12 under an alternate converter in our pre-registered robustness check. The lab, not the ecosystem, is the unit at which cooperative disposition is set; treating "Chinese models" as a monolith is not supported by the evidence.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 9 of its 20 references that are in the map. First posted on arXiv 10 Aug 2026.
Builds on
9 of 20 references.
Closest ancestors · 2
Same direction, newest first
- 2024Cultural Evolution of Cooperation among LLM Agents13 Dec
- 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr
Other references · 7
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2020Measuring Massive Multitask Language Understandingcited by 7,768
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
- 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
- 2016An open reproducible framework for the study of the iterated prisoner's dilemmacited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
- 2026Payoff scaling shapes cooperation in LLM agents across languages
- 2026Collective cooperation without individual fidelity in LLM agents
- 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma
- 2026Emergence of Reputation-Based Cooperation in LLM Agents
- 2024Static network structure cannot stabilize cooperation among Large Language Model agents
- 2026More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
- 2026Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation