2026-09-18T22:54:52Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1629262025-10-07T04:13:15Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Andreas, Jacob
Zhu, Sebastian
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-10-06T17:35:03Z
2025-10-06T17:35:03Z
2025-05
2025-06-23T14:04:53.393Z
https://hdl.handle.net/1721.1/162926
Current language models are limited in their ability to solve complex planning and reasoning problems without the aid of search procedures. While a large body of work has developed search procedures tailored to single-turn, single-user natural language interactions, language generation in multi-agent contexts involving multiple users, imperfect information, and partially misaligned objectives remains extremely challenging. We aim to build search procedures that will enable language models to assist with interactive, multi-agent decision-making in a diverse range of contexts. Using the word game Codenames as a benchmark, we will combine game-theoretic planning procedures with basic language model-based scoring methods to create agents that both play strong policies and play well with human policies. This work yields a set of practical text generation procedures, new evaluation benchmarks, and foundational algorithmic improvements in language model search.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Towards a Strong, Human-Compatible Codenames AI
Agent
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="28f7d078-8114-407d-8490-2d2f362fbe37">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Towards a Strong, Human-Compatible Codenames AI
Agent</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Zhu, Sebastian</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Current language models are limited in their ability to solve complex planning and reasoning problems without the aid of search procedures. While a large body of work has developed search procedures tailored to single-turn, single-user natural language interactions, language generation in multi-agent contexts involving multiple users, imperfect information, and partially misaligned objectives remains extremely challenging. We aim to build search procedures that will enable language models to assist with interactive, multi-agent decision-making in a diverse range of contexts. Using the word game Codenames as a benchmark, we will combine game-theoretic planning procedures with basic language model-based scoring methods to create agents that both play strong policies and play well with human policies. This work yields a set of practical text generation procedures, new evaluation benchmarks, and foundational algorithmic improvements in language model search.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>