{"id":"W4414360553","doi":"10.24963/ijcai.2025/26","title":"Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences","year":2025,"lang":"en","type":"article","venue":"","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Social dilemma; Set (abstract data type); Exploit; Dilemma; Term (time); Resolution (logic)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002997146,0.0006449448,0.0004340333,0.0005330868,0.001005518,0.002182229,0.001077459,0.001337785,0.002452698],"category_scores_gemma":[0.01329511,0.0003013314,0.0006953054,0.0002905501,0.001845734,0.002528307,0.00310433,0.001542679,0.0002472152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009904824,"about_ca_system_score_gemma":0.001278121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001501636,"about_ca_topic_score_gemma":0.002104448,"domain_scores_codex":[0.9980382,0.001262643,0.00008394534,0.000236598,0.0002515985,0.0001269002],"domain_scores_gemma":[0.9941556,0.003593521,0.0009444526,0.0005203305,0.0003095399,0.00047648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007736784,0.0008381853,0.04031081,0.0004795516,0.0003362527,0.002119096,0.01431094,0.4265438,0.0389853,0.327421,0.003432629,0.1444486],"study_design_scores_gemma":[0.00009174853,0.0002027397,0.002460594,0.00004166474,0.00007687232,0.0002631689,0.001540795,0.8488624,0.003557533,0.136143,0.006687857,0.00007156772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5419297,0.0001980606,0.4346893,0.00206326,0.00007457652,0.0002792906,0.00006854749,0.0004654477,0.02023183],"genre_scores_gemma":[0.918649,0.000050414,0.0794302,0.0001688204,0.00001446996,0.0001525247,0.00004200769,0.00002279077,0.00146989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002997146,"threshold_uncertainty_score":0.0158506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01962800160367494,"score_gpt":0.2936798427476764,"score_spread":0.2740518411440014,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}