Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916770557722624 |
|---|---|
| author | Zhou, Yufa Wang, Shaobo Dong, Xingyu Jin, Xiangqi Chen, Yifang Min, Yue Yang, Kexin Ren, Xingzhang Liu, Dayiheng Zhang, Linfeng |
| author_facet | Zhou, Yufa Wang, Shaobo Dong, Xingyu Jin, Xiangqi Chen, Yifang Min, Yue Yang, Kexin Ren, Xingzhang Liu, Dayiheng Zhang, Linfeng |
| contents | Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real-world applications such as market design, resource allocation, and policy analysis. We introduce $\textbf{Recon}$ ($\textbf{R}$easoning like an $\textbf{ECON}$omist), a 7B-parameter open-source LLM post-trained on a hand-curated dataset of 2,100 high-quality economic reasoning problems. Comprehensive evaluation on economic reasoning benchmarks and multi-agent games reveals clear improvements in structured reasoning and economic rationality. These results underscore the promise of domain-aligned post-training for enhancing reasoning and agent alignment, shedding light on the roles of SFT and RL in shaping model behavior. Code is available at https://github.com/MasterZhou1/Recon . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00577 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs Zhou, Yufa Wang, Shaobo Dong, Xingyu Jin, Xiangqi Chen, Yifang Min, Yue Yang, Kexin Ren, Xingzhang Liu, Dayiheng Zhang, Linfeng Artificial Intelligence Computation and Language Computer Science and Game Theory Multiagent Systems Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real-world applications such as market design, resource allocation, and policy analysis. We introduce $\textbf{Recon}$ ($\textbf{R}$easoning like an $\textbf{ECON}$omist), a 7B-parameter open-source LLM post-trained on a hand-curated dataset of 2,100 high-quality economic reasoning problems. Comprehensive evaluation on economic reasoning benchmarks and multi-agent games reveals clear improvements in structured reasoning and economic rationality. These results underscore the promise of domain-aligned post-training for enhancing reasoning and agent alignment, shedding light on the roles of SFT and RL in shaping model behavior. Code is available at https://github.com/MasterZhou1/Recon . |
| title | Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs |
| topic | Artificial Intelligence Computation and Language Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2506.00577 |