Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems

As artificial intelligence increasingly permeates everyday life, the development of Large Language Models (LLMs) capable of effectively simulating complex social interactions and fostering cooperative behavior has become paramount. This paper explores the enhancement of cooperative capabilities in L...

Full description

Autores:
Ortiz Almanza, David Santiago
Tipo de recurso:
Trabajo de grado de pregrado
Fecha de publicación:
2024
Institución:
Universidad de los Andes
Repositorio:
Séneca: repositorio Uniandes
Idioma:
eng
OAI Identifier:
oai:repositorio.uniandes.edu.co:1992/74464
Acceso en línea:
https://hdl.handle.net/1992/74464
Palabra clave:
Communication
Cooperation
Artificial intelligence
Large language models
Melting Pot
Ingeniería
Rights
embargoedAccess
License
Attribution-NonCommercial 4.0 International
id UNIANDES2_d408874261c9beb4f58b6a7d66b091a2
oai_identifier_str oai:repositorio.uniandes.edu.co:1992/74464
network_acronym_str UNIANDES2
network_name_str Séneca: repositorio Uniandes
repository_id_str
dc.title.eng.fl_str_mv Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
title Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
spellingShingle Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
Communication
Cooperation
Artificial intelligence
Large language models
Melting Pot
Ingeniería
title_short Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
title_full Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
title_fullStr Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
title_full_unstemmed Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
title_sort Enhancing multi-agent cooperation: the implementation and impact of a communication module in AI systems
dc.creator.fl_str_mv Ortiz Almanza, David Santiago
dc.contributor.advisor.none.fl_str_mv Manrique Piramanrique, Rubén Francisco
dc.contributor.author.none.fl_str_mv Ortiz Almanza, David Santiago
dc.subject.keyword.eng.fl_str_mv Communication
Cooperation
Artificial intelligence
Large language models
topic Communication
Cooperation
Artificial intelligence
Large language models
Melting Pot
Ingeniería
dc.subject.keyword.none.fl_str_mv Melting Pot
dc.subject.themes.spa.fl_str_mv Ingeniería
description As artificial intelligence increasingly permeates everyday life, the development of Large Language Models (LLMs) capable of effectively simulating complex social interactions and fostering cooperative behavior has become paramount. This paper explores the enhancement of cooperative capabilities in LLM-augmented Autonomous Agents (LAAs) through the integration of a dedicated communication module. Initial findings indicate that this module significantly enhances collaborative outcomes by enabling agents to share observations and insights, thereby fostering a more comprehensive understanding of their environment. This enhanced understanding has resulted in a 45% increase in per capita reward. Moreover, improved communication has facilitated more sustainable resource management and refined behavioral predictions among agents, leading to more strategic planning in multi-agent systems. Furthermore, the establishment of consensus through communication has proven invaluable in coordinating actions and promoting increased cooperation. However, the research also uncovers that while inter-agent communication can augment cooperation, it introduces risks of bias and misinformation.
publishDate 2024
dc.date.accessioned.none.fl_str_mv 2024-07-05T13:16:15Z
dc.date.issued.none.fl_str_mv 2024-07-04
dc.date.accepted.none.fl_str_mv 2024-07-04
dc.date.available.none.fl_str_mv 2025-05-30
dc.type.none.fl_str_mv Trabajo de grado - Pregrado
dc.type.driver.none.fl_str_mv info:eu-repo/semantics/bachelorThesis
dc.type.version.none.fl_str_mv info:eu-repo/semantics/acceptedVersion
dc.type.coar.none.fl_str_mv http://purl.org/coar/resource_type/c_7a1f
dc.type.content.none.fl_str_mv Text
dc.type.redcol.none.fl_str_mv http://purl.org/redcol/resource_type/TP
format http://purl.org/coar/resource_type/c_7a1f
status_str acceptedVersion
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/1992/74464
dc.identifier.instname.none.fl_str_mv instname:Universidad de los Andes
dc.identifier.reponame.none.fl_str_mv reponame:Repositorio Institucional Séneca
dc.identifier.repourl.none.fl_str_mv repourl:https://repositorio.uniandes.edu.co/
url https://hdl.handle.net/1992/74464
identifier_str_mv instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.references.none.fl_str_mv Press, O.U.: Cooperation. https://www.oed.com/search/dictionary/?scope=Entries&q=cooperation. Oxford English Dictionary, accessed: 15/02/2024 (2023)
Dafoe, A., Hughes, E., Bachrach, Y., Collins, T., McKee, K.R., Leibo, J.Z., Larson, K., Graepel, T.: Open Problems in Cooperative AI (2020)
Yousri, R., Essam, Z., Kareem, Y., Sherief, Y., Gamil, S., Safwat, S.: Illusionx: An llm-powered mixed reality personal companion (2024) https://doi.org/10.36227/techrxiv.170775603.33253596/v1
Agapiou, J.P., Vezhnevets, A.S., Du´e˜nez-Guzm´an, E.A., Matyas, J., Mao, Y., Sunehag, P., K¨oster, R., Madhushani, U., Kopparapu, K., Comanescu, R., Strouse, D., Johanson, M.B., Singh, S., Haas, J., Mordatch, I., Mobbs, D., Leibo, J.Z.: Melting Pot 2.0 (2023)
Mosquera, M., Pinzon, J.S., Rios, M., Fonseca, Y., Giraldo, L.F., Quijano, N., Manrique, R.: Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot (2024)
Park, J.S., O’Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative Agents: Interactive Simulacra of Human Behavior (2023)
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., Sun, M.: ChatDev: Communicative Agents for Software Development (2024)
Rasal, S.: LLM Harmony: Multi-Agent Communication for Problem Solving (2024)
Leibo, J.Z., nez-Guzm´an, E.D., Vezhnevets, A.S., Agapiou, J.P., Sunehag, P., Koster, R., Matyas, J., Beattie, C., Mordatch, I., Graepel, T.: Scalable evaluation of multi-agent reinforcement learning with melting pot. (2021). https://doi.org/10.48550/arXiv.2107.06857 . PMLR. https://doi.org/10.48550/arXiv.2107.06857
Pinzón Roncancio, J.S.: Large language models como planeadores multiagente en entornos sociales. Technical report, Universidad de los Andes (2024). https://hdl.handle.net/1992/73756
GoOpenAI: ChromaDB: An Open Source Vector Database. Blog Post. Image inspired by content available at https://blog.gopenai.com/chromadb-an-open-source-vector-database-f1871580b412 (2023).
dc.rights.en.fl_str_mv Attribution-NonCommercial 4.0 International
dc.rights.uri.none.fl_str_mv http://creativecommons.org/licenses/by-nc/4.0/
dc.rights.accessrights.none.fl_str_mv info:eu-repo/semantics/embargoedAccess
dc.rights.coar.none.fl_str_mv http://purl.org/coar/access_right/c_f1cf
rights_invalid_str_mv Attribution-NonCommercial 4.0 International
http://creativecommons.org/licenses/by-nc/4.0/
http://purl.org/coar/access_right/c_f1cf
eu_rights_str_mv embargoedAccess
dc.format.extent.none.fl_str_mv 41 páginas
dc.format.mimetype.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidad de los Andes
dc.publisher.program.none.fl_str_mv Ingeniería de Sistemas y Computación
dc.publisher.faculty.none.fl_str_mv Facultad de Ingeniería
dc.publisher.department.none.fl_str_mv Departamento de Ingeniería de Sistemas y Computación
publisher.none.fl_str_mv Universidad de los Andes
institution Universidad de los Andes
bitstream.url.fl_str_mv https://repositorio.uniandes.edu.co/bitstreams/0637aa71-6de8-4fe3-a42f-ed532311932f/download
https://repositorio.uniandes.edu.co/bitstreams/2ef89ff3-9fab-417a-8fd1-7143d4e0cf58/download
https://repositorio.uniandes.edu.co/bitstreams/3ff58a1d-b8c7-4bb1-b1a1-f77bcc315059/download
https://repositorio.uniandes.edu.co/bitstreams/38a47ad4-98be-4c02-9a43-bd6bbb5e1604/download
https://repositorio.uniandes.edu.co/bitstreams/439c08a8-5bde-4905-b187-fcb8137c1b2f/download
https://repositorio.uniandes.edu.co/bitstreams/c6668682-9c8b-411f-b6ba-a45ecdeb5898/download
https://repositorio.uniandes.edu.co/bitstreams/4a710541-269f-4721-b557-1b484b46e1ce/download
https://repositorio.uniandes.edu.co/bitstreams/6980f5e4-68b1-465a-be9e-fe54ed4bf402/download
bitstream.checksum.fl_str_mv a9a475c22294f3259c745fad95bf6503
1ed790ae2d878296e18c11abe1ed2db5
24013099e9e6abb1575dc6ce0855efd5
ae9e573a68e7f92501b6913cc846c39f
1a08b18a46e9aa9af136533ec1f8057f
530d320eb9a3b695b3582e4fc981c68e
f97f16203896584e386a444b5c09491b
b5d34c3ec4477df5c66eacf97c5b1164
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional Séneca
repository.mail.fl_str_mv adminrepositorio@uniandes.edu.co
_version_ 1812133973955969024
spelling Manrique Piramanrique, Rubén Franciscovirtual::18603-1Ortiz Almanza, David Santiago2024-07-05T13:16:15Z2025-05-302024-07-042024-07-04https://hdl.handle.net/1992/74464instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/As artificial intelligence increasingly permeates everyday life, the development of Large Language Models (LLMs) capable of effectively simulating complex social interactions and fostering cooperative behavior has become paramount. This paper explores the enhancement of cooperative capabilities in LLM-augmented Autonomous Agents (LAAs) through the integration of a dedicated communication module. Initial findings indicate that this module significantly enhances collaborative outcomes by enabling agents to share observations and insights, thereby fostering a more comprehensive understanding of their environment. This enhanced understanding has resulted in a 45% increase in per capita reward. Moreover, improved communication has facilitated more sustainable resource management and refined behavioral predictions among agents, leading to more strategic planning in multi-agent systems. Furthermore, the establishment of consensus through communication has proven invaluable in coordinating actions and promoting increased cooperation. However, the research also uncovers that while inter-agent communication can augment cooperation, it introduces risks of bias and misinformation.Pregrado41 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería de Sistemas y ComputaciónAttribution-NonCommercial 4.0 Internationalhttp://creativecommons.org/licenses/by-nc/4.0/info:eu-repo/semantics/embargoedAccesshttp://purl.org/coar/access_right/c_f1cfEnhancing multi-agent cooperation: the implementation and impact of a communication module in AI systemsTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPCommunicationCooperationArtificial intelligenceLarge language modelsMelting PotIngenieríaPress, O.U.: Cooperation. https://www.oed.com/search/dictionary/?scope=Entries&q=cooperation. Oxford English Dictionary, accessed: 15/02/2024 (2023)Dafoe, A., Hughes, E., Bachrach, Y., Collins, T., McKee, K.R., Leibo, J.Z., Larson, K., Graepel, T.: Open Problems in Cooperative AI (2020)Yousri, R., Essam, Z., Kareem, Y., Sherief, Y., Gamil, S., Safwat, S.: Illusionx: An llm-powered mixed reality personal companion (2024) https://doi.org/10.36227/techrxiv.170775603.33253596/v1Agapiou, J.P., Vezhnevets, A.S., Du´e˜nez-Guzm´an, E.A., Matyas, J., Mao, Y., Sunehag, P., K¨oster, R., Madhushani, U., Kopparapu, K., Comanescu, R., Strouse, D., Johanson, M.B., Singh, S., Haas, J., Mordatch, I., Mobbs, D., Leibo, J.Z.: Melting Pot 2.0 (2023)Mosquera, M., Pinzon, J.S., Rios, M., Fonseca, Y., Giraldo, L.F., Quijano, N., Manrique, R.: Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot (2024)Park, J.S., O’Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative Agents: Interactive Simulacra of Human Behavior (2023)Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., Sun, M.: ChatDev: Communicative Agents for Software Development (2024)Rasal, S.: LLM Harmony: Multi-Agent Communication for Problem Solving (2024)Leibo, J.Z., nez-Guzm´an, E.D., Vezhnevets, A.S., Agapiou, J.P., Sunehag, P., Koster, R., Matyas, J., Beattie, C., Mordatch, I., Graepel, T.: Scalable evaluation of multi-agent reinforcement learning with melting pot. (2021). https://doi.org/10.48550/arXiv.2107.06857 . PMLR. https://doi.org/10.48550/arXiv.2107.06857Pinzón Roncancio, J.S.: Large language models como planeadores multiagente en entornos sociales. Technical report, Universidad de los Andes (2024). https://hdl.handle.net/1992/73756GoOpenAI: ChromaDB: An Open Source Vector Database. Blog Post. Image inspired by content available at https://blog.gopenai.com/chromadb-an-open-source-vector-database-f1871580b412 (2023).201913600Publication9f6e12e0-098e-4548-ab81-75552e8385e7virtual::18603-19f6e12e0-098e-4548-ab81-75552e8385e7virtual::18603-1ORIGINALEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdfEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdfRestricción de acceso hasta mayo del 2025. Se pretenden utilizar el trabajo realizado y los resultados obtenidos como base de nuevas investigaciones.application/pdf781981https://repositorio.uniandes.edu.co/bitstreams/0637aa71-6de8-4fe3-a42f-ed532311932f/downloada9a475c22294f3259c745fad95bf6503MD51autorizacion tesis ISIS DS signed v2.pdfautorizacion tesis ISIS DS signed v2.pdfHIDEapplication/pdf238636https://repositorio.uniandes.edu.co/bitstreams/2ef89ff3-9fab-417a-8fd1-7143d4e0cf58/download1ed790ae2d878296e18c11abe1ed2db5MD52CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8914https://repositorio.uniandes.edu.co/bitstreams/3ff58a1d-b8c7-4bb1-b1a1-f77bcc315059/download24013099e9e6abb1575dc6ce0855efd5MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/38a47ad4-98be-4c02-9a43-bd6bbb5e1604/downloadae9e573a68e7f92501b6913cc846c39fMD54TEXTEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdf.txtEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdf.txtExtracted texttext/plain88354https://repositorio.uniandes.edu.co/bitstreams/439c08a8-5bde-4905-b187-fcb8137c1b2f/download1a08b18a46e9aa9af136533ec1f8057fMD55autorizacion tesis ISIS DS signed v2.pdf.txtautorizacion tesis ISIS DS signed v2.pdf.txtExtracted texttext/plain1176https://repositorio.uniandes.edu.co/bitstreams/c6668682-9c8b-411f-b6ba-a45ecdeb5898/download530d320eb9a3b695b3582e4fc981c68eMD57THUMBNAILEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdf.jpgEnhancing_Multi_Agent_Cooperation__The_Implementation_and_Impact_of_a_Communication_Module_in_AI_Systems.pdf.jpgGenerated Thumbnailimage/jpeg7709https://repositorio.uniandes.edu.co/bitstreams/4a710541-269f-4721-b557-1b484b46e1ce/downloadf97f16203896584e386a444b5c09491bMD56autorizacion tesis ISIS DS signed v2.pdf.jpgautorizacion tesis ISIS DS signed v2.pdf.jpgGenerated Thumbnailimage/jpeg11151https://repositorio.uniandes.edu.co/bitstreams/6980f5e4-68b1-465a-be9e-fe54ed4bf402/downloadb5d34c3ec4477df5c66eacf97c5b1164MD581992/74464oai:repositorio.uniandes.edu.co:1992/744642024-07-08 03:07:27.788http://creativecommons.org/licenses/by-nc/4.0/Attribution-NonCommercial 4.0 Internationalrestrictedhttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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