{"ID":2879843,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15510","arxiv_id":"2508.15510","title":"Super-additive Cooperation in Language Model Agents","abstract":"With the prospect of autonomous artificial intelligence (AI) agents, studying their tendency for cooperative behavior becomes an increasingly relevant topic. This study is inspired by the super-additive cooperation theory, where the combined effects of repeated interactions and inter-group rivalry have been argued to be the cause for cooperative tendencies found in humans. We devised a virtual tournament where language model agents, grouped into teams, face each other in a Prisoner's Dilemma game. By simulating both internal team dynamics and external competition, we discovered that this blend substantially boosts both overall and initial, one-shot cooperation levels (the tendency to cooperate in one-off interactions). This research provides a novel framework for large language models to strategize and act in complex social scenarios and offers evidence for how intergroup competition can, counter-intuitively, result in more cooperative behavior. These insights are crucial for designing future multi-agent AI systems that can effectively work together and better align with human values. Source code is available at https://github.com/pippot/Superadditive-cooperation-LLMs.","short_abstract":"With the prospect of autonomous artificial intelligence (AI) agents, studying their tendency for cooperative behavior becomes an increasingly relevant topic. This study is inspired by the super-additive cooperation theory, where the combined effects of repeated interactions and inter-group rivalry have been argued to b...","url_abs":"https://arxiv.org/abs/2508.15510","url_pdf":"https://arxiv.org/pdf/2508.15510v1","authors":"[\"Filippo Tonini\",\"Lukas Galke\"]","published":"2025-08-21T12:36:44Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":610634,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879843,"paper_url":"https://arxiv.org/abs/2508.15510","paper_title":"Super-additive Cooperation in Language Model Agents","repo_url":"https://github.com/pippot/Superadditive-cooperation-LLMs","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}