{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162926"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162926","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Towards a Strong, Human-Compatible Codenames AI Agent","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_html":"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_has_math":false,"creators":["Zhu, Sebastian"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Andreas, Jacob"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:21:02Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/162926","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Andreas, Jacob"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Zhu, Sebastian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-06T17:35:03Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-10-06T17:35:03Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/162926"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Towards a Strong, Human-Compatible Codenames AI Agent"]}]}],"canonical_facts":{"dc:contributor.advisor":["Andreas, Jacob"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Zhu, Sebastian"],"dc:date.accessioned":["2025-10-06T17:35:03Z"],"dc:date.available":["2025-10-06T17:35:03Z"],"dc:date.issued":["2025-05"],"dc:description.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."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162926"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Towards a Strong, Human-Compatible Codenames AI Agent"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:02Z"}