{"type":"ScholarlyArticle","title":"Emergence of Social Norms in Generative Agent Societies: Principles and Architecture","authors":[{"name":"Siyue Ren","slug":"siyue-ren","given":"Siyue","family":"Ren","affiliation":"School of Mechanical Engineering , Northwestern Polytechnical University"},{"name":"Zhiyao Cui","slug":"zhiyao-cui","given":"Zhiyao","family":"Cui","affiliation":"School of Cybersecurity , Northwestern Polytechnical University"},{"name":"Ruiqi Song","slug":"ruiqi-song","given":"Ruiqi","family":"Song","affiliation":"School of Cybersecurity , Northwestern Polytechnical University"},{"name":"Zhen Wang","slug":"zhen-wang","given":"Zhen","family":"Wang","affiliation":"School of Mechanical Engineering , Northwestern Polytechnical University; School of Cybersecurity , Northwestern Polytechnical University; School of Artificial Intelligence, OPtics and ElectroNics(iOPEN) , Northwestern Polytechnical University"},{"name":"Shuyue Hu","slug":"shuyue-hu","given":"Shuyue","family":"Hu","affiliation":"Shanghai Artificial Intelligence Laboratory"}],"abstract":"Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to be normative. In this paper, we propose a novel architecture, named CRSEC, to empower the emergence of social norms within generative MASs. Our architecture consists of four modules: Creation & Representation, Spreading, Evaluation, and Compliance. This addresses several important aspects of the emergent processes all in one: (i) where social norms come from, (ii) how they are formally represented, (iii) how they spread through agents' communications and observations, (iv) how they are examined with a sanity check and synthesized in the long term, and (v) how they are incorporated into agents' planning and actions. Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs. The positive outcomes of our human evaluation, conducted with 30 evaluators, further affirm the effectiveness of our approach. Our project can be accessed via the following link: https://github.com/sxswz213/CRSEC.","doi":"10.24963/ijcai.2024/874","url":"https://ijcai.org/proceedings/2024/874","pdf":"https://ijcai.org/proceedings/2024/0874.pdf","markdown":"https://ijcai.org/proceedings/2024/874.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/874","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Human-Centred AI","track":"Human-Centred AI","number":874,"pages":{"first":7895,"last":7903},"keywords":["Agent-based and Multi-agent Systems: MAS: Agent societies","Agent-based and Multi-agent Systems: MAS: Normative systems","Machine Learning: ML: Applications","Agent-based and Multi-agent Systems: MAS: Agent-based simulation and emergence"],"videos":[],"references":[{"position":1,"raw":"[Abbink et al., 2017] K. Abbink, Lata G., Toby Handfield, and John Thrasher. Peer punishment promotes enforce- ment of bad social norms. Nature communications, 2017.","title":"Peer punishment promotes enforcement of bad social norms","authors":"K Abbink, G Lata, Toby Handfield, John Thrasher","year":"2017","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Abid et al., 2021] Abubakar Abid, Maheen Farooqi, and James Zou. Persistent anti-muslim bias in large language models. In AIES, pages 298-306, 2021.","title":"Persistent anti-muslim bias in large language models","authors":"Abubakar Abid, Maheen Farooqi, James Zou","year":"2021","venue":"AIES","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ågotnes et al., 2009] T. Ågotnes, W. Van Der Hoek, J. A Rodríguez-Aguilar, C. Sierra, and M. Wooldridge. A tem- poral logic of normative systems. In Towards Mathemati- cal Philosophy: Papers from the Studia Logica conference Trends in Logic IV, pages 69-106. Springer, 2009.","title":"A temporal logic of normative systems","authors":"T Ågotnes, W Van Der Hoek, J A Rodríguez-Aguilar, C Sierra, M Wooldridge","year":"2009","venue":"Towards Mathematical Philosophy: Papers from the Studia Logica conference Trends in Logic IV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ajmeri et al., 2020] Nirav Ajmeri, Hui Guo, Pradeep K Mu- rukannaiah, and Munindar P Singh. Elessar: Ethics in norm-aware agents. In AAMAS, pages 16-24, 2020.","title":"Elessar: Ethics in norm-aware agents","authors":"Nirav Ajmeri, Hui Guo, K Pradeep, Munindar P Murukannaiah, Singh","year":"2020","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Argente et al., 2020] Estefania Argente, Elena Del Val, Daniel P., and Vicente B. Normative emotional agents: a viewpoint paper. IEEE Trans. Affective Comput., 2020.","title":"Normative emotional agents: a viewpoint paper","authors":"Estefania Argente, Elena Del Val, Daniel P, Vicente B","year":"2020","venue":"IEEE Trans. Affective Comput","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Awad et al., 2018] Edmond Awad, Sohan D., Richard Kim, Jonathan S., Joseph H., Azim S., Jean-Franc ¸ois B., and Iyad R. The moral machine experiment. Nature, 2018.","title":"The moral machine experiment","authors":"Edmond Awad, D Sohan, Richard Kim, Jonathan S Joseph, H Azim, S Jean-Franc ¸ois, B Iyad, R","year":"2018","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Beheshti and Sukthankar, 2014] Rahmatollah Beheshti and Gita Sukthankar. A normative agent-based model for pre- dicting smoking cessation trends. In AAMAS, 2014.","title":"Rahmatollah Beheshti and Gita Sukthankar. A normative agent-based model for predicting smoking cessation trends","authors":"Sukthankar Beheshti","year":"2014","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Beheshti et al., 2015] Rahmatollah Beheshti, Awrad M. Ali, and Gita S. Cognitive social learners: An architecture for modeling normative behavior. In AAAI, 2015.","title":"Cognitive social learners: An architecture for modeling normative behavior","authors":"Beheshti","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Boella et al., 2008] Guido Boella, Leendert Van Der Torre, and Harko Verhagen. Introduction to the special issue on normative multiagent systems. AAMAS, 17:1-10, 2008.","title":"Introduction to the special issue on normative multiagent systems","authors":"Guido Boella, Leendert Van Der, Torre, Harko Verhagen","year":"2008","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Bratman, 1987] Michael Bratman. Intention, plans, and practical reason. 1987.","title":"Intention, plans, and practical reason","authors":"Michael Bratman","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Centola et al., 2018] D. Centola, J. Becker, D. Brackbill, and A. Baronchelli. Experimental evidence for tipping points in social convention. Science, 360(6393), 2018.","title":"Experimental evidence for tipping points in social convention","authors":"D Centola, J Becker, D Brackbill, A Baronchelli","year":"6393","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Chugunova and Sele, 2022] Marina Chugunova and Daniela Sele. We and it: An interdisciplinary review of the experimental evidence on how humans interact with machines. Journal of Behavioral and Experimental Economics, 99:101897, 2022.","title":"Marina Chugunova and Daniela Sele. We and it: An interdisciplinary review of the experimental evidence on how humans interact with machines","authors":"Sele Chugunova","year":"2022","venue":"Journal of Behavioral and Experimental Economics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Cialdini et al., 1991] Robert B Cialdini, Carl A Kallgren, and Raymond R Reno. A focus theory of normative con- duct: A theoretical refinement and reevaluation of the role of norms in human behavior. In Advances in experimental social psychology, volume 24. 1991.","title":"A focus theory of normative conduct: A theoretical refinement and reevaluation of the role of norms in human behavior","authors":"Carl A Robert B Cialdini, Raymond R Kallgren, Reno","year":"1991","venue":"Advances in experimental social psychology","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Clark et al., 2021] E. Clark, T. August, S. Serrano, N. Haduong, S. Gururangan, and N. A. Smith. All that's' human'is not gold: Evaluating human evaluation of gener- ated text. arXiv:2107.00061, 2021.","title":"All that's' human'is not gold: Evaluating human evaluation of generated text","authors":"E Clark, T August, S Serrano, N Haduong, S Gururangan, N A Smith","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Conte et al., 1998] R. Conte, C. Cristiano, and D. Frank. Autonomous norm acceptance. In ATAL Workshop, 1998.","title":"Autonomous norm acceptance","authors":"R Conte, C Cristiano, D Frank","year":"1998","venue":"ATAL Workshop","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Criado et al., 2011] Natalia Criado, Estefania Argente, and V Botti. Open issues for normative multi-agent systems. AI communications, 2011.","title":"Open issues for normative multi-agent systems","authors":"Natalia Criado, Estefania Argente, Botti","year":"2011","venue":"AI communications","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Dignum, 1999] Frank Dignum. Autonomous agents with norms. Artificial intelligence and law, 7:69-79, 1999.","title":"Autonomous agents with norms","authors":"Frank Dignum","year":"1999","venue":"Artificial intelligence and law","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Franks et al., 2013] Henry Franks, Nathan Griffiths, and Sarabjot Singh Anand. Learning influence in complex so- cial networks. In AAMAS, 2013.","title":"Learning influence in complex social networks","authors":"Franks","year":"2013","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Guo et al., 2023] Siyi Guo, Negar Mokhberian, and Kristina Lerman. A data fusion framework for multi- domain morality learning. In AAAI, 2023.","title":"A data fusion framework for multidomain morality learning","authors":"Siyi Guo, Negar Mokhberian, Kristina Lerman","year":"2023","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Hämmerl et al., 2022] K. Hämmerl, B. Deiseroth, P. Schramowski, J. Libovickỳ, A. Fraser, and K. Kersting. Do multilingual language models capture differing moral norms? arXiv preprint arXiv:2203.09904, 2022.","title":"Do multilingual language models capture differing moral norms","authors":"K Hämmerl, B Deiseroth, P Schramowski, J Libovickỳ, A Fraser, K Kersting","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Haque and Singh, 2024] A. Haque and M. P. Singh. Ex- tracting norms from contracts via chatgpt: Opportunities and challenges. In COINE workshop, AAMAS, 2024.","title":"Extracting norms from contracts via chatgpt: Opportunities and challenges","authors":"Haque, ; A Singh, M P Haque, Singh","year":"2024","venue":"COINE workshop, AAMAS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Hawkins et al., 2019] Robert XD Hawkins, Noah D G., and Robert L G. The emergence of social norms and conven- tions. Trends in cognitive sciences, 2019.","title":"The emergence of social norms and conventions","authors":"X D Robert, Hawkins, D G Noah, Robert L G","year":"2019","venue":"Trends in cognitive sciences","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Haynes et al., 2017] Chris Haynes, Michael Luck, Peter McBurney, Samhar Mahmoud, Tomáš Vítek, and Simon Miles. Engineering the emergence of norms: a review. The Knowledge Engineering Review, 2017.","title":"Engineering the emergence of norms: a review","authors":"Chris Haynes, Michael Luck, Peter Mcburney, Samhar Mahmoud, Tomáš Vítek, Simon Miles","year":"2017","venue":"The Knowledge Engineering Review","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[He et al., 2024] Shawn He, Surangika Ranathunga, Stephen Cranefield, and Bastin Tony Roy Savarimuthu. Norm vi- olation detection in multi-agent systems using large lan- guage models: A pilot study. In COINE workshop, AA- MAS, 2024.","title":"Norm violation detection in multi-agent systems using large language models: A pilot study","authors":"Shawn He, Surangika Ranathunga, Stephen Cranefield, Bastin Tony, Roy Savarimuthu","year":"2024","venue":"COINE workshop","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Hong et al., 2023] S. Hong, X. Zheng, J. Chen, Y. Cheng, J. Wang, C. Zhang, Z. Wang, S. K. S. Yau, Z. Lin, L. Zhou, et al. Metagpt: Meta programming for multi-agent collab- orative framework. arXiv:2308.00352, 2023.","title":"Metagpt: Meta programming for multi-agent collaborative framework","authors":"S Hong, X Zheng, J Chen, Y Cheng, J Wang, C Zhang, Z Wang, S K S Yau, Z Lin, L Zhou","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Hu and Leung, 2017] Shuyue Hu and Ho-fung Leung. Achieving coordination in multi-agent systems by stable local conventions under community networks. In IJCAI, 2017.","title":"Achieving coordination in multi-agent systems by stable local conventions under community networks","authors":"Leung Hu, Shuyue Hu, Ho-Fung Leung","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/659"},{"position":27,"raw":"[Hu et al., 2019] Shuyue Hu, Chin-wing Leung, Ho-fung Leung, and Jiamou Liu. To be big picture thinker or detail- oriented? utilizing perceived gist information to achieve efficient convention emergence with bilateralism and mul- tilateralism. In AAMAS, 2019.","title":"To be big picture thinker or detailoriented? utilizing perceived gist information to achieve efficient convention emergence with bilateralism and multilateralism","authors":"Hu","year":"2019","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Lewis, 1969] David Kellogg Lewis. Convention: A philo- sophical study. 1969.","title":"Convention: A philosophical study","authors":"David Kellogg, Lewis","year":"1969","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Li et al., 2024] Shimin Li, Tianxiang Sun, and Xipeng Qiu. Agent alignment in evolving social norms. arXiv preprint arXiv:2401.04620, 2024.","title":"Agent alignment in evolving social norms","authors":"Shimin Li, Tianxiang Sun, Xipeng Qiu","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Lin et al., 2023] B. Yuchen Lin, Y. Fu, K. Yang, Prithviraj A., Faeze B., S. Huang, Chandra B., Y. Choi, and X. Ren. Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks. In NeurIPS, 2023.","title":"Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks","authors":"B Yuchen Lin, Y Fu, K Yang, A Prithviraj, B Faeze, S Huang, Chandra B, Y Choi, X Ren","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Liu et al., 2024] R. Liu, R. Yang, C. Jia, G. Zhang, D. Yang, and S. Vosoughi. Training socially aligned language mod- els on simulated social interactions. In ICLR, 2024.","title":"Training socially aligned language models on simulated social interactions","authors":"R Liu, R Yang, C Jia, G Zhang, D Yang, S Vosoughi","year":"2024","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Mahmoud et al., 2015] S. Mahmoud, G. Nathan, J. Kep- pens, A. Taweel, T. JM Bench-Capon, and M. Luck. Es- tablishing norms with metanorms in distributed computa- tional systems. Artificial Intelligence and Law, 2015.","title":"Establishing norms with metanorms in distributed computational systems","authors":"S Mahmoud, G Nathan, J Keppens, A Taweel, T Jm Bench-Capon, M Luck","year":"2015","venue":"Artificial Intelligence and Law","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Mahmoud et al., 2017] S. Mahmoud, N. Griffiths, J. Kep- pens, and M. Luck. Establishing norms with metanorms over interaction topologies. AAMAS, 2017.","title":"Establishing norms with metanorms over interaction topologies","authors":"S Mahmoud, N Griffiths, J Keppens, M Luck","year":"2017","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Modgil et al., 2009] S. Modgil, N. Faci, F. Meneguzzi, N. Oren, S. Miles, and M. Luck. A framework for moni- toring agent-based normative systems. In AAMAS, 2009.","title":"A framework for monitoring agent-based normative systems","authors":"S Modgil, N Faci, F Meneguzzi, N Oren, S Miles, M Luck","year":"2009","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Morales et al., 2013] Javier Morales, Maite Lopez- Sanchez, Juan A Rodriguez-Aguilar, M. J Wooldridge, and Wamberto W. Vasconcelos. Automated synthesis of normative systems. In AAMAS, 2013.","title":"Automated synthesis of normative systems","authors":"Javier Morales, Maite Lopez-Sanchez, Juan A Rodriguez-Aguilar, M J Wooldridge, Wamberto W Vasconcelos","year":"2013","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Morales et al., 2015] Javier Morales, Maite López- Sánchez, Juan Antonio Rodríguez-Aguilar, Michael Wooldridge, and Wamberto Vasconcelos. Synthesising liberal normative systems. In AAMAS, 2015.","title":"Synthesising liberal normative systems","authors":"Javier Morales, Maite López-Sánchez, Juan Antonio Rodríguez-Aguilar, Michael Wooldridge, Wamberto Vasconcelos","year":"2015","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Morris-Martin et al., 2019] Andreasa Morris-Martin, Ma- rina De Vos, and Julian Padget. Norm emergence in mul- tiagent systems: a viewpoint paper. AAMAS, 2019.","title":"Andreasa Morris-Martin, Ma","authors":"Morris-Martin","year":"2019","venue":"Norm emergence in multiagent systems: a viewpoint paper","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Nakamaru and Levin, 2004] Mayuko Nakamaru and S. A Levin. Spread of two linked social norms on complex in- teraction networks. Journal of theoretical biology, 2004.","title":"Spread of two linked social norms on complex interaction networks","authors":"Mayuko Nakamaru, S A Levin","year":"2004","venue":"Journal of theoretical biology","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Nyla R. Branscombe, 2022] Robert A. Baron Nyla R. Branscombe. Social Psychology 15th ed. 2022.","title":"Social Psychology","authors":"Robert A Baron Nyla, R Branscombe","year":"2022","venue":"Social Psychology","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Paiva et al., 2018] A. Paiva, F. Santos, and F. Santos. En- gineering pro-sociality with autonomous agents. In AAAI, 2018.","title":"Engineering pro-sociality with autonomous agents","authors":"A Paiva, F Santos, F Santos","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Park et al., 2023] J. S. Park, J. C. O'Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein. Generative agents: Interactive simulacra of human behavior. In UIST '23. As- sociation for Computing Machinery, 2023.","title":"Generative agents: Interactive simulacra of human behavior","authors":"J S Park, J C O'brien, C J Cai, M R Morris, P Liang, M S Bernstein","year":"2023","venue":"UIST '23","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Ramezani and Xu, 2023] A. Ramezani and Y. Xu. Knowl- edge of cultural moral norms in large language models. ACL, 2023.","title":"Knowledge of cultural moral norms in large language models","authors":"Xu Ramezani, A Ramezani, Y Xu","year":"2023","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Santos et al., 2017] Jéssica S Santos, Jean O Zahn, Ed- uardo A Silvestre, Viviane T Silva, and Wamberto W Vas- concelos. Detection and resolution of normative conflicts in multi-agent systems: a literature survey. AAMAS, 2017.","title":"Detection and resolution of normative conflicts in multi-agent systems: a literature survey","authors":"Jean O Jéssica S Santos, Eduardo A Zahn, Silvestre, T Viviane, Wamberto W Silva, Vasconcelos","year":"2017","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Santos et al., 2018] Fernando Santos, Jorge Pacheco, and Francisco Santos. Social norms of cooperation with costly reputation building. In AAAI, volume 32, 2018.","title":"Social norms of cooperation with costly reputation building","authors":"Santos","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Savarimuthu and Cranefield, 2011] Bastin Tony Roy Savarimuthu and Stephen Cranefield. Norm creation, spreading and emergence: A survey of simulation models of norms in multi-agent systems. Multiagent and Grid Systems, 7(1):21-54, 2011.","title":"Norm creation, spreading and emergence: A survey of simulation models of norms in multi-agent systems","authors":"Bastin Tony, Roy Savarimuthu, Stephen Cranefield","year":"2011","venue":"Multiagent and Grid Systems","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Savarimuthu et al., 2009] Bastin Tony Roy Savarimuthu, Maryam Purvis, Martin Purvis, and Stephen Cranefield. Social norm emergence in virtual agent societies. In DALT 2008: Revised Selected and Invited Papers, 2009.","title":"Social norm emergence in virtual agent societies","authors":"Bastin Tony, Roy Savarimuthu, Maryam Purvis, Martin Purvis, Stephen Cranefield","year":"2009","venue":"DALT 2008: Revised Selected and Invited Papers","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Savarimuthu et al., 2024] Bastin Tony Roy Savarimuthu, Surangika Ranathunga, and Stephen Cranefield. Harness- ing the power of llms for normative reasoning in mass. In COINE workshop, AAMAS, 2024.","title":"Harnessing the power of llms for normative reasoning in mass","authors":"Bastin Tony, Roy Savarimuthu, Surangika Ranathunga, Stephen Cranefield","year":"2024","venue":"COINE workshop, AAMAS","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Schramowski et al., 2022] Patrick Schramowski, Cigdem T., Nico A., Constantin A R., and Kristian K. Large pre-trained language models contain human-like biases of what is right and wrong to do. Nature Mach. Intell., 2022.","title":"Large pre-trained language models contain human-like biases of what is right and wrong to do","authors":"Patrick Schramowski, T Cigdem, A Nico, A R Constantin, Kristian K","year":"2022","venue":"Nature Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Schwartz, 1973] S. H. Schwartz. Normative explanations of helping behavior: A critique, proposal, and empirical test. Journal of Experimental Social Psychology, 1973.","title":"Normative explanations of helping behavior: A critique, proposal, and empirical test","authors":"S H Schwartz","year":"1973","venue":"Journal of Experimental Social Psychology","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Sen and Airiau, 2007] S. Sen and S. Airiau. Emergence of norms through social learning. In IJCAI, 2007.","title":"Emergence of norms through social learning","authors":"S Sen, S Airiau","year":"2007","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2007/243"},{"position":51,"raw":"[Shanahan et al., 2023] M. Shanahan, K. M., and L. R. Role play with large language models. Nature, 2023.","title":"Role play with large language models","authors":"M Shanahan, K M, L R","year":"2023","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Sherif, 1936] Muzafer Sherif. The psychology of social norms. Harper, 1936.","title":"The psychology of social norms","authors":"Muzafer Sherif","year":"1936","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Shettleworth, 2009] Sara J Shettleworth. Cognition, evolu- tion, and behavior. Oxford university press, 2009.","title":"Cognition, evolution, and behavior","authors":"J Sara, Shettleworth","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Sunstein, 1996] Cass R Sunstein. Social norms and social roles. Colum. L. Rev., 96:903, 1996.","title":"Social norms and social roles","authors":"Cass R Sunstein","year":"1996","venue":"Colum. L. Rev","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Villatoro et al., 2011] Daniel Villatoro, Giulia A., Jordi Sabater-Mir, and Rosaria Conte. Dynamic sanctioning for robust and cost-efficient norm compliance. In IJCAI, 2011.","title":"Dynamic sanctioning for robust and cost-efficient norm compliance","authors":"Daniel Villatoro, A Giulia, Rosaria Jordi Sabater-Mir, Conte","year":"2011","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/77"},{"position":56,"raw":"[Wang et al., 2023] Z. Wang, S. Cai, G. Chen, A. Liu, X. Ma, and Y. Liang. Describe, explain, plan and select: inter- active planning with llms enables open-world multi-task agents. In NeurIPS, 2023.","title":"Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents","authors":"Z Wang, S Cai, G Chen, A Liu, X Ma, Y Liang","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Winikoff and Sidorenko, 2023] Michael Winikoff and Galina Sidorenko. Evaluating a mechanism for explaining bdi agent behaviour. In AAMAS, 2023.","title":"Evaluating a mechanism for explaining bdi agent behaviour","authors":"Sidorenko Winikoff, Michael Winikoff, Galina Sidorenko","year":"2023","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Winikoff et al., 2021] Michael Winikoff, Galina S., Virginia D., and Frank D. Why bad coffee? explaining bdi agent behaviour with valuings. Artificial Intelligence, 2021.","title":"Why bad coffee? explaining bdi agent behaviour with valuings","authors":"Michael Winikoff, Galina S Virginia, D, Frank D","year":"2021","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Yao and Logan, 2016] Yuan Yao and Brian Logan. Action- level intention selection for bdi agents. 2016.","title":"Actionlevel intention selection for bdi agents","authors":"Yuan Yao, Brian Logan","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Young, 2015] H Peyton Young. The evolution of social norms. economics, 7(1):359-387, 2015.","title":"The evolution of social norms","authors":"Young Peyton","year":"2015","venue":"economics","doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Zhang et al., 2024] H. Zhang, W. Du, J. Shan, Q. Zhou, Y. Du, B. T. Joshua, T. Shu, and C. Gan. Building co- operative embodied agents modularly with large language models. In ICLR, 2024.","title":"Building cooperative embodied agents modularly with large language models","authors":"H Zhang, W Du, J Shan, Q Zhou, Y Du, B T Joshua, T Shu, C Gan","year":"2024","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}