Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01708 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910008502910976 |
|---|---|
| author | Cui, Langyuan Ling, Chun Kai Ng, Hwee Tou |
| author_facet | Cui, Langyuan Ling, Chun Kai Ng, Hwee Tou |
| contents | Large Language Models (LLMs) are increasingly deployed in real-world scenarios where they may lack sufficient information to complete a given task. In such settings, the ability to actively seek out missing information becomes a critical capability. Existing approaches to enhancing this ability often rely on simplifying assumptions that degrade \textit{worst-case} performance. This is an issue with serious implications in high-stakes applications. In this work, we use the game of Twenty Questions to evaluate the information-seeking ability of LLMs. We introduce and formalize its adversarial counterpart, the Strategic Language Search (SLS) problem along with its variants as a two-player zero-sum extensive form game. We propose Game of Thought (GoT), a framework that applies game-theoretic techniques to approximate a Nash equilibrium (NE) strategy for the restricted variant of the game. Empirical results demonstrate that our approach consistently improves worst-case performance compared to (1) direct prompting-based methods and (2) heuristic-guided search methods across all tested settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01708 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory Cui, Langyuan Ling, Chun Kai Ng, Hwee Tou Computation and Language Artificial Intelligence Computer Science and Game Theory I.2.7; I.2.8 Large Language Models (LLMs) are increasingly deployed in real-world scenarios where they may lack sufficient information to complete a given task. In such settings, the ability to actively seek out missing information becomes a critical capability. Existing approaches to enhancing this ability often rely on simplifying assumptions that degrade \textit{worst-case} performance. This is an issue with serious implications in high-stakes applications. In this work, we use the game of Twenty Questions to evaluate the information-seeking ability of LLMs. We introduce and formalize its adversarial counterpart, the Strategic Language Search (SLS) problem along with its variants as a two-player zero-sum extensive form game. We propose Game of Thought (GoT), a framework that applies game-theoretic techniques to approximate a Nash equilibrium (NE) strategy for the restricted variant of the game. Empirical results demonstrate that our approach consistently improves worst-case performance compared to (1) direct prompting-based methods and (2) heuristic-guided search methods across all tested settings. |
| title | Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory |
| topic | Computation and Language Artificial Intelligence Computer Science and Game Theory I.2.7; I.2.8 |
| url | https://arxiv.org/abs/2602.01708 |