{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001678378,0.00008353644,0.0001315965,0.0000297947,0.0001913865,0.00006896083,0.0001571491,0.00005160842,0.00003014283],"category_scores_gemma":[0.00001076401,0.00006309016,0.00003259841,0.0002381133,0.00005886832,0.0002050071,0.00001956215,0.00007174437,0.000003749198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001894636,"about_ca_system_score_gemma":0.0001102907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000249774,"about_ca_topic_score_gemma":0.0001100328,"domain_scores_codex":[0.9991853,0.00007992845,0.0002324814,0.0001952952,0.0002014476,0.0001055915],"domain_scores_gemma":[0.9995009,0.00005635219,0.000158242,0.0001404421,0.0001235591,0.0000204505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009574433,0.0006574466,0.08325217,0.0009786478,0.0003996491,0.0000404604,0.01402312,0.0035806,0.1004519,0.6760992,0.01023068,0.1101904],"study_design_scores_gemma":[0.00323383,0.0003076459,0.05088492,0.0005652501,0.00006059196,0.0000110237,0.001026439,0.6891397,0.2489289,0.002142614,0.003105056,0.0005940712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1913673,0.00003350273,0.8031309,0.003617855,0.0003618305,0.0002532815,0.000002722234,0.00008534535,0.001147312],"genre_scores_gemma":[0.9856098,5.572225e-7,0.01375004,0.0004883473,0.00005447084,0.00001036755,0.00000569372,0.000002344257,0.00007842437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7942425,"threshold_uncertainty_score":0.2572742,"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."}}