{"id":"W4410087623","doi":"10.1109/wi-iat62293.2024.00074","title":"Evaluating and Enhancing LLMs Agent Based on Theory of Mind in Guandan: A Multi-Player Cooperative Game Under Imperfect Information","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Imperfect; Perfect information; Computer science; Game theory; Mathematical economics; Economics; Philosophy","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":[0.003669408,0.0009542301,0.0008031665,0.0004925639,0.0006557163,0.001384177,0.00192289,0.001287161,0.00319752],"category_scores_gemma":[0.01368882,0.0004073431,0.0006371855,0.0002386657,0.001417596,0.00277631,0.002502251,0.001700308,0.0004592577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508169,"about_ca_system_score_gemma":0.00255299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009721257,"about_ca_topic_score_gemma":0.01602367,"domain_scores_codex":[0.9985885,0.0007912758,0.00006683839,0.0002463418,0.0001807555,0.0001263912],"domain_scores_gemma":[0.9937649,0.004515551,0.0004230685,0.000512725,0.0004501351,0.0003336177],"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":[0.0007422439,0.0007384665,0.007632362,0.0003945187,0.0001337798,0.0004610024,0.00103709,0.8775352,0.006823116,0.02236158,0.002340333,0.07980033],"study_design_scores_gemma":[0.00002860054,0.0001412642,0.0002372933,0.00001077657,0.00001455158,0.00001982349,0.00007228402,0.9930784,0.001221899,0.004466647,0.0006959868,0.00001237169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4799693,0.0002210784,0.504391,0.000940376,0.0001340664,0.000618036,0.0002496406,0.003309896,0.01016659],"genre_scores_gemma":[0.8674666,0.00006363077,0.1294053,0.000202622,0.000008669152,0.0003169085,0.0002133614,0.0001239829,0.002198976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009721257,"threshold_uncertainty_score":0.01940596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0727216316583185,"score_gpt":0.3662076669918495,"score_spread":0.293486035333531,"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."}}