{"id":"W4392223779","doi":"10.24963/ijcai.2024/26","title":"Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Game Theory and Voting Systems","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Engineering and Physical Sciences Research Council; University of Oxford; Good Ventures Foundation","keywords":"Delegation; Control (management); Business; Computer security; Computer science; Political science; Artificial intelligence; Law","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":[0.002962033,0.0006367418,0.0005029588,0.0004913082,0.0009129385,0.002019462,0.001052196,0.001412018,0.00250683],"category_scores_gemma":[0.01292042,0.0003056323,0.0007207665,0.0002898089,0.001905371,0.002392164,0.002871157,0.001583126,0.0002376779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009746199,"about_ca_system_score_gemma":0.001124633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001612938,"about_ca_topic_score_gemma":0.002058165,"domain_scores_codex":[0.998062,0.001251126,0.00008113481,0.0002499492,0.0002265932,0.000129287],"domain_scores_gemma":[0.9938875,0.003898397,0.0009224996,0.0005032649,0.0002884704,0.0004999188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000564195,0.0005815424,0.02743731,0.0003437143,0.0002859581,0.001309543,0.007246063,0.4608959,0.02524356,0.3751729,0.002789131,0.09813015],"study_design_scores_gemma":[0.00008540929,0.0001410201,0.001728565,0.00002608189,0.00005324514,0.0001437306,0.0007348775,0.8245441,0.002146032,0.1660724,0.004276911,0.00004773123],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.5072069,0.000180467,0.4716184,0.002288157,0.00007024611,0.0002224932,0.0000744245,0.0003452185,0.0179937],"genre_scores_gemma":[0.9249194,0.00005345176,0.0728684,0.000179589,0.00001893522,0.0001458096,0.00004286564,0.00002124072,0.001750196],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.002962033,"threshold_uncertainty_score":0.01566494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05002284425876859,"score_gpt":0.2756504319227501,"score_spread":0.2256275876639816,"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."}}