Towards a Strong, Human-Compatible Codenames AI
Agent
Name
zhu-sebaszhu-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
1.2 MB
Format
Adobe PDF
Checksum (MD5)
e32506ec750bb49ff7f6468e7f3b6094
Author(s)
Zhu, Sebastian
Advisor(s)
Andreas, Jacob
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
