Game-theoretic LLM: Agent Workflow for Negotiation Games
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917834432446464 |
|---|---|
| author | Hua, Wenyue Liu, Ollie Li, Lingyao Amayuelas, Alfonso Chen, Julie Jiang, Lucas Jin, Mingyu Fan, Lizhou Sun, Fei Wang, William Wang, Xintong Zhang, Yongfeng |
| author_facet | Hua, Wenyue Liu, Ollie Li, Lingyao Amayuelas, Alfonso Chen, Julie Jiang, Lucas Jin, Mingyu Fan, Lizhou Sun, Fei Wang, William Wang, Xintong Zhang, Yongfeng |
| contents | This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory. We evaluate several state-of-the-art LLMs across a spectrum of complete-information and incomplete-information games. Our findings reveal that LLMs frequently deviate from rational strategies, particularly as the complexity of the game increases with larger payoff matrices or deeper sequential trees.
To address these limitations, we design multiple game-theoretic workflows that guide the reasoning and decision-making processes of LLMs. These workflows aim to enhance the models' ability to compute Nash Equilibria and make rational choices, even under conditions of uncertainty and incomplete information. Experimental results demonstrate that the adoption of these workflows significantly improves the rationality and robustness of LLMs in game-theoretic tasks. Specifically, with the workflow, LLMs exhibit marked improvements in identifying optimal strategies, achieving near-optimal allocations in negotiation scenarios, and reducing susceptibility to exploitation during negotiations. Furthermore, we explore the meta-strategic considerations of whether it is rational for agents to adopt such workflows, recognizing that the decision to use or forgo the workflow constitutes a game-theoretic issue in itself.
Our research contributes to a deeper understanding of LLMs' decision-making capabilities in strategic contexts and provides insights into enhancing their rationality through structured workflows. The findings have implications for the development of more robust and strategically sound AI agents capable of navigating complex interactive environments. Code and data supporting this study are available at \url{https://github.com/Wenyueh/game_theory}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05990 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Game-theoretic LLM: Agent Workflow for Negotiation Games Hua, Wenyue Liu, Ollie Li, Lingyao Amayuelas, Alfonso Chen, Julie Jiang, Lucas Jin, Mingyu Fan, Lizhou Sun, Fei Wang, William Wang, Xintong Zhang, Yongfeng Artificial Intelligence Computation and Language Computer Science and Game Theory Machine Learning Multiagent Systems This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory. We evaluate several state-of-the-art LLMs across a spectrum of complete-information and incomplete-information games. Our findings reveal that LLMs frequently deviate from rational strategies, particularly as the complexity of the game increases with larger payoff matrices or deeper sequential trees. To address these limitations, we design multiple game-theoretic workflows that guide the reasoning and decision-making processes of LLMs. These workflows aim to enhance the models' ability to compute Nash Equilibria and make rational choices, even under conditions of uncertainty and incomplete information. Experimental results demonstrate that the adoption of these workflows significantly improves the rationality and robustness of LLMs in game-theoretic tasks. Specifically, with the workflow, LLMs exhibit marked improvements in identifying optimal strategies, achieving near-optimal allocations in negotiation scenarios, and reducing susceptibility to exploitation during negotiations. Furthermore, we explore the meta-strategic considerations of whether it is rational for agents to adopt such workflows, recognizing that the decision to use or forgo the workflow constitutes a game-theoretic issue in itself. Our research contributes to a deeper understanding of LLMs' decision-making capabilities in strategic contexts and provides insights into enhancing their rationality through structured workflows. The findings have implications for the development of more robust and strategically sound AI agents capable of navigating complex interactive environments. Code and data supporting this study are available at \url{https://github.com/Wenyueh/game_theory}. |
| title | Game-theoretic LLM: Agent Workflow for Negotiation Games |
| topic | Artificial Intelligence Computation and Language Computer Science and Game Theory Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2411.05990 |